© 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. 28-GEMMASCOPE-RES-16K
    11. 8206
    Prev
    Next
    INDEX
    Explanations

    numerical values and their significance in various contexts

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

    Looks for numbers enclosed in parentheses

    np_acts-logits-general · gemini-2.0-flash

    numbers and code surrounding certain phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🎰
    -0.33
     Stell
    -0.31
    WebServlet
    -0.31
     vicin
    -0.30
     beira
    -0.30
    prüfung
    -0.30
    
    -0.29
    EndInit
    -0.28
    AndEndTag
    -0.28
    ม้
    -0.28
    POSITIVE LOGITS
     مرئيه
    0.68
    ActionCreators
    0.59
    rungsseite
    0.56
     intStringLen
    0.53
    fatta
    0.51
     ProtoMessage
    0.51
    RenderAtEndOf
    0.50
    Tembelea
    0.48
    complexContent
    0.48
     Савезне
    0.48
    Activations Density 0.099%

    No Known Activations