© 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. 6379
    Prev
    Next
    INDEX
    Explanations

    specific scientific techniques and processes in laboratory settings

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

    beads, resins, and columns

    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
    CompilerServices
    -0.42
     Roskov
    -0.37
    FormTagHelper
    -0.35
    goon
    -0.35
     envíos
    -0.34
     emisiones
    -0.33
    Ծանոթ
    -0.33
     begleiten
    -0.32
    Únete
    -0.32
     lähe
    -0.31
    POSITIVE LOGITS
     immobilized
    0.85
    immobili
    0.78
     immobili
    0.75
     Immobili
    0.73
    Immobili
    0.71
     beads
    0.70
     resins
    0.65
     resin
    0.63
     bead
    0.63
     columns
    0.63
    Activations Density 0.274%

    No Known Activations