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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20171
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or instructions related to actions

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

    following punctuation or sequence markers

    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
    AddTagHelper
    -0.83
    tvguidetime
    -0.81
    +#+
    -0.79
    TagMode
    -0.77
    endpush
    -0.75
    drawal
    -0.74
    MigrationBuilder
    -0.72
    MLLoader
    -0.71
    makeConstraints
    -0.71
     introspection
    -0.71
    POSITIVE LOGITS
    ByDefault
    0.30
     Deshalb
    0.24
    isNullOrEmpty
    0.23
    indest
    0.23
    那就
    0.22
     duly
    0.22
     altrett
    0.22
     warto
    0.21
     zostały
    0.21
     Simply
    0.21
    Activations Density 0.051%

    No Known Activations