© 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. 11842
    Prev
    Next
    INDEX
    Explanations

    terms related to experimental procedures and methodologies

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

    technical terms or phrases within academic, scientific, or programming contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    language describing formal procedures, tests, or phases in technical contexts, often within enumerations or methodological statements.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    tokens in procedural or technical contexts, particularly in scientific papers, code, and formal documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    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
     HttpNotFound
    -0.75
     Италијани
    -0.64
     ligiloj
    -0.63
    Tembelea
    -0.63
    GEBURTSDATUM
    -0.59
     дописавши
    -0.56
     snippetHide
    -0.55
    WarningLevel
    -0.54
     onAnimation
    -0.53
    ﹧
    -0.53
    POSITIVE LOGITS
     thereafter
    0.41
     adaptarse
    0.34
    
    0.33
     thence
    0.33
    StartTag
    0.33
     subsequently
    0.32
     subsequent
    0.31
    EndInit
    0.29
     přip
    0.29
     afterward
    0.29
    Activations Density 0.574%

    No Known Activations