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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14805
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislative actions and political discussions

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

    Statements about future plans

    np_acts-logits-general · gemini-2.0-flash

    recent or future plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.61
    atangan
    -0.51
    lenir
    -0.48
     olur
    -0.47
    IntoConstraints
    -0.46
    Weblinks
    -0.44
    волю
    -0.43
    elerik
    -0.43
     become
    -0.43
    цезда
    -0.42
    POSITIVE LOGITS
     recently
    1.23
    recently
    1.17
     Recently
    1.07
     currently
    1.05
    Recently
    1.04
     recientemente
    1.01
     recentemente
    1.00
    currently
    0.97
     has
    0.96
     недавно
    0.94
    Activations Density 0.612%

    No Known Activations