© 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. 82398
    Prev
    Next
    INDEX
    Explanations

    programming class declarations and static methods or properties

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

    I and we narrating actions

    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
    ProgressHUD
    -0.38
    sizePolicy
    -0.37
     piz
    -0.37
     outputStream
    -0.36
    velocity
    -0.36
     Pil
    -0.34
     Pa
    -0.34
    re
    -0.34
    جا
    -0.34
    cipar
    -0.33
    POSITIVE LOGITS
     disambiguazione
    0.79
    +#+
    0.65
    
    0.63
     kasarigan
    0.54
     שוליים
    0.54
    SequentialGroup
    0.53
    Referencies
    0.52
    phosa
    0.50
    AndEndTag
    0.49
     autorytatywna
    0.48
    Activations Density 0.076%

    No Known Activations