© 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. 18-GEMMASCOPE-RES-16K
    11. 14764
    Prev
    Next
    INDEX
    Explanations

    declarations of variables in programming code

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

    JavaScript variable declaration: "var"

    np_acts-logits-general · gemini-2.0-flash

    javascript variable declarations

    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
     оригіналу
    -1.02
     تضيفلها
    -0.90
    '>{
    -0.89
    Santi
    -0.85
     itſelf
    -0.84
     ་་
    -0.80
    +#+#
    -0.77
     Isis
    -0.76
     Visconti
    -0.75
     defaultstate
    -0.75
    POSITIVE LOGITS
    var
    0.89
     var
    0.82
    fvar
    0.81
     Var
    0.71
    VAR
    0.66
     vars
    0.65
     VAR
    0.65
     kvar
    0.62
     חיצוניים
    0.61
    argout
    0.60
    Activations Density 0.022%

    No Known Activations