© 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. 16-GEMMASCOPE-RES-16K
    11. 10838
    Prev
    Next
    INDEX
    Explanations

    blocks of code or documentation comments

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

    Code, especially comments or imports

    np_acts-logits-general · gemini-2.0-flash

    code delimiters and block starts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ']='
    -0.60
    بوابة
    -0.57
     PopupWindow
    -0.56
    жнее
    -0.56
    Personensuche
    -0.55
    edip
    -0.55
    sider
    -0.54
    '=>'
    -0.54
     Wainwright
    -0.53
    ']->
    -0.52
    POSITIVE LOGITS
    endphp
    0.79
     mergeFrom
    0.69
    tagHelperRunner
    0.66
    estacks
    0.63
    cookieParser
    0.57
     resourceCulture
    0.57
    Jeografia
    0.56
    ValueStyle
    0.56
    SourceChecksum
    0.55
     simplifié
    0.55
    Activations Density 0.072%

    No Known Activations