© 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. 17-GEMMASCOPE-RES-16K
    6. 6796
    Prev
    Next
    INDEX
    Explanations

    variables and their declarations in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     برانيه
    -0.74
    BoxShadow
    -0.67
    ceni
    -0.65
    CloseOperation
    -0.63
    談社
    -0.61
    thansa
    -0.61
    zyński
    -0.60
    Santi
    -0.59
    蒙
    -0.59
     Héctor
    -0.59
    POSITIVE LOGITS
    fvar
    1.18
     StringVar
    1.11
     Variables
    1.04
     vars
    0.99
     VAR
    0.96
    Variables
    0.95
    VAR
    0.92
     Vars
    0.91
     Var
    0.90
     variables
    0.90
    Activations Density 0.099%

    No Known Activations