© 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 EvalsExportsinterp-engineNEWAPI 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. 88372
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components and their interactions

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

    jsfiddle links

    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
     []:
    -0.35
     canal
    -0.35
    @(
    -0.33
    ########.
    -0.32
    @
    -0.32
     head
    -0.31
    möbel
    -0.31
    getID
    -0.31
    Canonical
    -0.30
    Queryable
    -0.30
    POSITIVE LOGITS
    toggler
    1.52
    DrawerToggle
    0.75
     autorytatywna
    0.71
    Cyfarwyddwr
    0.69
    ientras
    0.61
    ніципалі
    0.60
    transQ
    0.59
    ItemBackground
    0.57
    WebServlet
    0.56
    #+#
    0.55
    Activations Density 0.001%

    No Known Activations