© 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
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11769
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific expressions or terms related to data analysis

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

    scientific notation and technical symbols in mathematical, chemical, and programming contexts.

    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
    ंदीखरीदारी
    -0.41
    verifyException
    -0.38
    ➟
    -0.38
    windowFixed
    -0.37
    ついで
    -0.35
    setof
    -0.35
     podjela
    -0.34
    AISSEE
    -0.33
     تخصص
    -0.32
    Joining
    -0.31
    POSITIVE LOGITS
     Normdatei
    0.74
    MigrationBuilder
    0.60
    tagHelperRunner
    0.60
    +#+#
    0.60
     الرياضيه
    0.56
    RenderAtEndOf
    0.51
    TagMode
    0.51
    +#+
    0.50
     الحره
    0.50
    ScopeManager
    0.49
    Activations Density 4.964%

    No Known Activations