© 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. 21-GEMMASCOPE-RES-16K
    11. 14952
    Prev
    Next
    INDEX
    Explanations

    declarations and structures in programming code, particularly related to access modifiers and method signatures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Long
    -0.63
    Long
    -0.55
    /
    -0.52
     The
    -0.51
     when
    -0.51
     &
    -0.49
    ###
    -0.48
     /
    -0.47
     to
    -0.46
     P
    -0.45
    POSITIVE LOGITS
    boolean
    1.41
     boolean
    1.34
    int
    1.33
    bool
    1.31
     int
    1.27
     bool
    1.25
    出版年
    1.10
    float
    1.07
     float
    1.01
    setVerticalGroup
    0.95
    Activations Density 0.108%

    No Known Activations