© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9650
    Prev
    Next
    INDEX
    Explanations

    import statements in programming code

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

    import statements in source code files.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    onOptions
    -0.65
    ьаж
    -0.60
    PyExc
    -0.57
    Климаты
    -0.57
     ब्रेकडाउन
    -0.57
    Ƚ
    -0.52
    
    -0.52
    ----</
    -0.52
     Infórmanos
    -0.52
     Photocase
    -0.51
    POSITIVE LOGITS
     android
    0.47
    Partager
    0.40
     javax
    0.39
    koh
    0.38
     jsPsych
    0.38
     Elles
    0.38
     seedlings
    0.37
     Sinal
    0.37
     FontWeight
    0.36
     Northern
    0.36
    Activations Density 0.026%

    No Known Activations