© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 69446
    Prev
    Next
    INDEX
    Explanations

    syntactic patterns in code, particularly focusing on structural elements such as braces and semicolons

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

    else or otherwise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новништво
    -0.47
     intptr
    -0.45
     CURIAM
    -0.43
    )$/,
    -0.41
     kaarangay
    -0.40
     незавершена
    -0.39
    ंदीखरीदारी
    -0.39
     Wiktionnaire
    -0.37
    genheim
    -0.37
     мәкал
    -0.35
    POSITIVE LOGITS
     otherwise
    3.50
     Otherwise
    3.11
    Otherwise
    3.05
    otherwise
    3.05
     OTHERWISE
    2.55
     altrimenti
    2.52
     else
    2.41
     sonst
    2.31
    否则
    2.30
    else
    2.27
    Activations Density 0.115%

    No Known Activations