© 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. 7-GEMMASCOPE-RES-16K
    11. 15897
    Prev
    Next
    INDEX
    Explanations

    labels, attributes, or keys related to data structure definitions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eventually
    -0.34
     
    -0.34
    me
    -0.31
     eventual
    -0.31
    uck
    -0.29
    1
    -0.29
     C
    -0.29
    ↵
    -0.29
     P
    -0.28
     Zus
    -0.28
    POSITIVE LOGITS
    SharedCtor
    0.95
    featureID
    0.95
    ########.
    0.90
     lenker
    0.89
    Personensuche
    0.88
     Италијани
    0.88
    expandindo
    0.87
    出版年
    0.87
     مشين
    0.84
    :✨
    0.84
    Activations Density 0.716%

    No Known Activations