© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3323
    Prev
    Next
    INDEX
    Explanations

    terms related to results or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code and programming-related tokens, particularly those related to error handling, result processing, and function calls.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ancha
    -0.66
    Concerning
    -0.63
    ifdef
    -0.63
     telefónica
    -0.60
     lebar
    -0.59
     ngang
    -0.57
     inalámbrica
    -0.56
     siquiera
    -0.55
     commerciali
    -0.54
     maș
    -0.54
    POSITIVE LOGITS
     result
    1.27
     Result
    1.16
    result
    1.14
     results
    1.12
    Result
    1.09
     RESULT
    1.05
     Results
    0.97
     getResult
    0.93
    results
    0.91
     resul
    0.90
    Activations Density 0.100%

    No Known Activations