© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7189
    Prev
    Next
    INDEX
    Explanations

    terms related to political integrity and ethics.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to financial matters and economic systems.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words and phrases related to strong desires, needs, or convictions. It activates for words like "desire", "need", "concern", "commitment", "conviction", "obsession", etc., especially when they are used in contexts expressing a strong feeling or motivation.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    states of mind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addContainerGap
    -0.58
    apnews
    -0.56
    DockStyle
    -0.56
    UnsafeEnabled
    -0.53
    aronne
    -0.52
    WebpackPlugin
    -0.52
    phorus
    -0.52
     &___
    -0.51
    utuhkan
    -0.51
    duce
    -0.50
    POSITIVE LOGITS
     Paglinawan
    0.57
    ">//
    0.57
     Chwiliwch
    0.56
     from
    0.54
     of
    0.53
    jsdelivr
    0.51
     célèbres
    0.51
    tagHelperRunner
    0.50
    Ẩ
    0.49
     terhadap
    0.48
    Activations Density 0.746%

    No Known Activations