© 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. 25-GEMMASCOPE-RES-16K
    11. 3719
    Prev
    Next
    INDEX
    Explanations

    structures of class and method declarations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     const
    -0.70
     bool
    -0.64
    nullptr
    -0.60
     nullptr
    -0.56
     readonly
    -0.55
     AspNetCore
    -0.53
     HasFactory
    -0.52
    foreach
    -0.52
     cout
    -0.51
     string
    -0.50
    POSITIVE LOGITS
    boolean
    1.05
    final
    1.00
    long
    0.90
    String
    0.84
    int
    0.81
     final
    0.80
     boolean
    0.79
    byte
    0.78
    StringBuffer
    0.76
    StringBuilder
    0.75
    Activations Density 0.229%

    No Known Activations