© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9382
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and chemical notations

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

    mathematical and scientific notation symbols including Greek letters, measurement units, and numeric values with special characters.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Rumble
    -0.51
    summary
    -0.49
    Summary
    -0.44
     collage
    -0.44
     Tiro
    -0.43
     leva
    -0.43
     potes
    -0.43
     summary
    -0.43
     IAP
    -0.42
    TIE
    -0.42
    POSITIVE LOGITS
    uxxxx
    0.81
     Autorisations
    0.65
     betweenstory
    0.60
     Autorizaciones
    0.60
    extré
    0.59
    ResponseWriter
    0.59
    addCriterion
    0.57
    EndInit
    0.56
     valentín
    0.56
    ientôt
    0.54
    Activations Density 0.738%

    No Known Activations