© 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. 42422
    Prev
    Next
    INDEX
    Explanations

    occurrences of compliance with established standards or protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    IContainer
    -0.77
     defaultstate
    -0.68
     }{@
    -0.57
     TextInputType
    -0.56
    ensement
    -0.56
    saraba
    -0.55
    webElementXpaths
    -0.55
     createSprite
    -0.54
    disposing
    -0.53
    listFiles
    -0.53
    POSITIVE LOGITS
     humanidade
    0.45
    HomeAsUpEnabled
    0.40
     parlato
    0.35
    ują
    0.35
    หญิง
    0.35
    humanité
    0.32
    untung
    0.32
    junior
    0.32
     tarihi
    0.31
     inversa
    0.31
    Activations Density 0.000%

    No Known Activations