© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 6714
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols, particularly related to equations or formulas in a comprehensive manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    es
    -0.69
    </strong>
    -0.62
    /
    -0.61
     Mar
    -0.61
     Ven
    -0.61
     C
    -0.60
     ven
    -0.58
     on
    -0.58
     Man
    -0.57
     Ver
    -0.56
    POSITIVE LOGITS
    \[
    1.34
     \[
    1.16
     myſelf
    1.08
     itſelf
    1.05
     uſ
    1.05
     ſtate
    1.05
     \]
    1.02
     ་་
    1.01
    \]
    1.01
     purpoſe
    1.01
    Activations Density 0.156%

    No Known Activations