© 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. 6401
    Prev
    Next
    INDEX
    Explanations

    references to fixed attributes or parameters in various contexts

    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
    AccessorTable
    -0.73
     <<<<<<<<<<<<<<
    -0.68
     שוליים
    -0.67
     ligiloj
    -0.64
    Sucesor
    -0.64
    DoubleQuotes
    -0.64
    @[+][
    -0.61
    ThroughAttribute
    -0.60
     }}"></
    -0.60
     cytok
    -0.59
    POSITIVE LOGITS
     fixed
    1.26
    fixed
    1.21
    Fixed
    1.20
    FIXED
    1.19
     Fixed
    1.18
     FIXED
    1.13
     fixe
    0.99
     fija
    0.93
    固定
    0.91
     fixa
    0.89
    Activations Density 0.420%

    No Known Activations