© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12816
    Prev
    Next
    INDEX
    Explanations

    patterns or structures in numerical data or data representations

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

    unintelligible/hard to understand

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    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
    ReusableCell
    -0.63
    存于互联网档案馆
    -0.57
    styleType
    -0.52
    enterOuterAlt
    -0.50
    AddTagHelper
    -0.50
    URLException
    -0.49
    MigrationBuilder
    -0.49
    ResponseWriter
    -0.49
     transfieras
    -0.48
    IsContent
    -0.47
    POSITIVE LOGITS
     strange
    0.77
     mysterious
    0.75
     unintelligible
    0.75
     mystérie
    0.73
     cryptic
    0.73
     incomp
    0.72
     seemingly
    0.70
     unclear
    0.69
     inexplicable
    0.69
     seems
    0.68
    Activations Density 0.583%

    No Known Activations