© 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. 4175
    Prev
    Next
    INDEX
    Explanations

    code-related terms, particularly those associated with functions and event handling

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

    Code snippets and programming-related text

    np_acts-logits-general · gemini-2.0-flash

    foreign words and code terms

    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
    aglia
    -0.58
    CUR
    -0.56
     and
    -0.54
    AsUp
    -0.54
     complex
    -0.54
    loria
    -0.53
     Gruber
    -0.52
    dropna
    -0.52
    himura
    -0.52
     club
    -0.52
    POSITIVE LOGITS
    انجليز
    0.76
     typelib
    0.69
     titolata
    0.68
    InjectAttribute
    0.65
    ViewFeatures
    0.65
     étoit
    0.64
     Dede
    0.64
    OGND
    0.64
     RUSH
    0.63
    msgTypes
    0.62
    Activations Density 0.146%

    No Known Activations