© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3932
    Prev
    Next
    INDEX
    Explanations

    code blocks, specifically the structure and flow control elements such as brackets and catch statements

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

    closing braces and catch blocks in exception handling code.

    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
     otherwise
    -0.76
    Otherwise
    -0.76
     altrimenti
    -0.69
     Otherwise
    -0.69
    otherwise
    -0.66
    不然
    -0.64
    elif
    -0.55
    否则
    -0.50
    elseif
    -0.50
     elseif
    -0.50
    POSITIVE LOGITS
    finally
    0.96
     finally
    0.94
     Finally
    0.75
     finalmente
    0.72
    終於
    0.71
     FINALLY
    0.70
    Finally
    0.69
    终于
    0.68
     Enfin
    0.67
     enfin
    0.67
    Activations Density 0.068%

    No Known Activations