© 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. 1-GEMMASCOPE-RES-16K
    6. 5782
    Prev
    Next
    INDEX
    Explanations

    terms related to programming interfaces and implementations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.62
    %")
    -0.58
    %");
    -0.57
    $")
    -0.52
     vettore
    -0.50
    HAEL
    -0.49
    ```
    
    -0.49
    ambito
    -0.48
    SPATH
    -0.47
     ذكر
    -0.46
    POSITIVE LOGITS
    awtextra
    0.86
     AttributeSet
    0.74
    writeFieldEnd
    0.71
     resourceCulture
    0.70
    ilya
    0.70
    AutoSize
    0.68
    hasMoreElements
    0.67
    MigrationBuilder
    0.66
    ConstraintMaker
    0.66
    ibatis
    0.63
    Activations Density 2.146%

    No Known Activations