© 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 EvalsExportsAPI 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. 117324
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the need for further research or investigation

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

    further investigation and testing

    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
    WebElementEntity
    -0.40
     perfectly
    -0.39
     Lag
    -0.35
     perfect
    -0.35
    Perfect
    -0.35
    Perfectly
    -0.34
     Perfect
    -0.34
     Ga
    -0.33
     Bres
    -0.33
    excell
    -0.33
    POSITIVE LOGITS
    principalColumn
    0.71
     AssemblyVersion
    0.69
     insuffisamment
    0.67
    MessageOf
    0.66
    AndEndTag
    0.65
     незавершена
    0.64
    URLException
    0.62
    Geplaatst
    0.62
    saraba
    0.62
     ویکی‌پدی
    0.62
    Activations Density 0.219%

    No Known Activations