© 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. 6632
    Prev
    Next
    INDEX
    Explanations

    code-related terms and data types in programming languages

    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
    endpush
    -0.49
     either
    -0.48
     ent
    -0.47
    m
    -0.47
     bound
    -0.46
    ​
    -0.46
     p
    -0.46
     In
    -0.45
    長の
    -0.45
    일에
    -0.45
    POSITIVE LOGITS
    CloseOperation
    0.99
     myſelf
    0.98
    ISupport
    0.98
     auffi
    0.96
     himſelf
    0.95
     reaſon
    0.95
     itſelf
    0.95
     Monfieur
    0.89
    InjectAttribute
    0.88
    NameInMap
    0.87
    Activations Density 0.105%

    No Known Activations