© 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. 12574
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and closing braces or brackets in programming syntax

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

    code snippets

    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
    ValueStyle
    -0.73
    ⟬
    -0.72
    ſelf
    -0.72
     itſelf
    -0.69
     BoxFit
    -0.68
     ProtoMessage
    -0.68
    ſelves
    -0.67
    存于互联网档案馆
    -0.65
    <unused16>
    -0.65
    <unused23>
    -0.65
    POSITIVE LOGITS
    ↵↵
    0.52
    ↵
    0.45
    </blockquote>
    0.42
    ↵↵↵
    0.41
    <em>
    0.41
    <strong>
    0.41
    ↵↵↵↵
    0.40
    Và
    0.40
    and
    0.40
     and
    0.40
    Activations Density 0.017%

    No Known Activations