© 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. 9712
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and arguments related to programming logic

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

    Spanish language text, particularly in technical or programming discussion contexts.

    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
    SequentialGroup
    -0.73
     surla
    -0.72
    complexContent
    -0.68
     '\\;'
    -0.68
     חיצוניים
    -0.67
     يتيمه
    -0.63
    tagHelperRunner
    -0.63
    IntoConstraints
    -0.63
     fédé
    -0.61
    BagConstraints
    -0.59
    POSITIVE LOGITS
     se
    0.51
     have
    0.37
     le
    0.37
     actually
    0.36
     normally
    0.35
     usually
    0.35
     are
    0.34
     can
    0.34
     tend
    0.33
    mbox
    0.32
    Activations Density 0.084%

    No Known Activations