© 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. 61470
    Prev
    Next
    INDEX
    Explanations

    terms related to revealing or disclosing information

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

    revealing or exposing

    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
    rrggbb
    -0.61
     Lari
    -0.56
     برانيه
    -0.56
    Bibliograf
    -0.49
    estacks
    -0.49
    DotNetBar
    -0.48
    KindOfClass
    -0.48
     Италијани
    -0.48
     jurado
    -0.48
    paravant
    -0.47
    POSITIVE LOGITS
     expose
    1.67
     exposes
    1.57
     exposing
    1.55
    expose
    1.48
     exposed
    1.34
    Expose
    1.33
    exposed
    1.20
    Exposed
    1.17
     Exposed
    1.17
     expos
    1.00
    Activations Density 0.010%

    No Known Activations