© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 46870
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to database management and schema definitions

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

    defining structure and components

    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
    IntoConstraints
    -0.73
    MLLoader
    -0.69
     Chwiliwch
    -0.66
    aarrggbb
    -0.65
    CPtr
    -0.64
    oredCriteria
    -0.63
    oneofs
    -0.60
    DockStyle
    -0.59
    يكب
    -0.59
     StringTokenizer
    -0.59
    POSITIVE LOGITS
     consists
    0.71
     consiste
    0.68
     consisting
    0.67
     consisted
    0.60
     consist
    0.58
     består
    0.52
     polega
    0.50
     состоит
    0.48
     składa
    0.46
     comprenant
    0.46
    Activations Density 0.308%

    No Known Activations