© 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. 9-GEMMASCOPE-RES-131K
    11. 82051
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connective phrases in text

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

    listing options or alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Становништво
    -0.50
     fédé
    -0.42
     rahasia
    -0.40
    แตก
    -0.40
     découver
    -0.40
     officielles
    -0.40
     lantaran
    -0.38
     enfans
    -0.38
     citoyens
    -0.38
    Autoritní
    -0.37
    POSITIVE LOGITS
     CreateTagHelper
    0.66
     Svensson
    0.47
    egrave
    0.47
     PRS
    0.47
    {!
    0.44
    녔
    0.44
    gom
    0.44
    encies
    0.44
     Це
    0.44
    orice
    0.44
    Activations Density 0.164%

    No Known Activations