© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 548
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

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

    mathematical notation and formatting in technical or academic documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    whitespace and structural formatting tokens (including newlines, tabs, and mathematical delimiters).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.81
     estekak
    -0.66
    Datuak
    -0.65
    ंदीखरीदारी
    -0.63
     ***!
    -0.63
     ComVisible
    -0.61
    évaluateur
    -0.60
     disambiguazione
    -0.60
    +#+
    -0.59
    aarrggbb
    -0.59
    POSITIVE LOGITS
     therefore
    0.57
     proof
    0.55
     Here
    0.52
     Let
    0.52
     Proof
    0.50
     $
    0.48
     let
    0.47
     Therefore
    0.47
     solution
    0.47
    Therefore
    0.46
    Activations Density 1.069%

    No Known Activations