Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 1590
    Prev
    Next
    INDEX
    Explanations

    variable and function declarations in a programming context

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

    code structure with `const`

    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
     colectiva
    -0.39
    NSNotification
    -0.37
     voluntarios
    -0.36
     mecánico
    -0.36
    abstractmethod
    -0.36
    ensuche
    -0.36
     amongst
    -0.35
     llorando
    -0.35
     виправивши
    -0.35
     obligado
    -0.34
    POSITIVE LOGITS
    ロウィン
    0.68
    msgTypes
    0.62
    ſehen
    0.59
    ]');
    0.59
    endphp
    0.57
     müſſen
    0.57
    mpagne
    0.57
    iſen
    0.57
    енча
    0.54
    richTextPanel
    0.54
    Activations Density 0.006%

    No Known Activations