© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9295
    Prev
    Next
    INDEX
    Explanations

    lines of code and preprocessor directives in programming syntax

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

    C preprocessor directives

    np_acts-logits-general · gemini-2.0-flash

    conditional compilation directives

    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
    $_['
    -0.59
     prisonniers
    -0.57
    SaveVideo
    -0.57
    ltä
    -0.56
     Wikiseite
    -0.55
    />";
    -0.55
     ambientale
    -0.54
     Milner
    -0.54
    λίου
    -0.54
    "]));
    -0.54
    POSITIVE LOGITS
    AxisAlignment
    0.91
    BeginInit
    0.81
    webElementGuid
    0.70
    VersionUID
    0.70
    tagHelperRunner
    0.69
    存于互联网档案馆
    0.68
    findpost
    0.63
     ModelExpression
    0.62
     Chwiliwch
    0.62
    новништво
    0.61
    Activations Density 0.085%

    No Known Activations