© 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. 6653
    Prev
    Next
    INDEX
    Explanations

    code components related to object-oriented programming, specifically involving class definitions and methods

    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
    şam
    -0.56
     Reverso
    -0.56
    TryGetValue
    -0.55
     Técnica
    -0.53
     faut
    -0.52
    imanapun
    -0.52
     références
    -0.52
    iastes
    -0.50
    owanym
    -0.47
     visible
    -0.46
    POSITIVE LOGITS
     الرياضيه
    0.63
     "..\..\..\
    0.63
    /******/
    0.63
    djangoproject
    0.61
    GraphicsUnit
    0.61
    енча
    0.58
    XmlAccessType
    0.58
    Попис
    0.58
    Personendaten
    0.57
    //
    0.57
    Activations Density 0.124%

    No Known Activations