© 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. 12-GEMMASCOPE-RES-16K
    11. 5665
    Prev
    Next
    INDEX
    Explanations

    references to entities and numerical values within text related to articles and various formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atu
    -0.33
    MAR
    -0.29
    pf
    -0.29
    分
    -0.27
     mot
    -0.27
     against
    -0.26
    <b>
    -0.26
    ย
    -0.26
     lf
    -0.25
     th
    -0.25
    POSITIVE LOGITS
    IUrlHelper
    0.73
    IntoConstraints
    0.70
     يتيمه
    0.70
     propOrder
    0.69
    arangay
    0.67
    WebElementEntity
    0.66
     nahilalakip
    0.66
    AndEndTag
    0.64
     Efq
    0.64
    ValueStyle
    0.63
    Activations Density 4.017%

    No Known Activations