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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5608
    Prev
    Next
    INDEX
    Explanations

    affirmative and negative statements about understanding and actions

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

    French negations or related adverbs

    np_acts-logits-general · gemini-2.0-flash

    does not work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zkod
    -0.47
    tinyurl
    -0.47
    InitStruct
    -0.45
    peño
    -0.45
    dragen
    -0.45
    ForValue
    -0.44
    ateness
    -0.44
    wäh
    -0.44
    itigation
    -0.44
    wini
    -0.44
    POSITIVE LOGITS
     infatti
    1.17
     indeed
    1.14
     obviously
    1.10
     nemlig
    1.09
     therefore
    1.09
     basically
    1.06
     usually
    1.04
     actually
    1.02
     bowiem
    0.98
     certainly
    0.98
    Activations Density 0.101%

    No Known Activations