© 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. 31-GEMMASCOPE-RES-16K
    11. 3638
    Prev
    Next
    INDEX
    Explanations

    specific formats and identifiers commonly used in programming and scientific notation

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

    letters (like "M." or "M_") that appear in academic, technical, or scientific notation.

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

    single letters followed by periods in abbreviated names and citations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.56
    ConstraintMaker
    -0.47
     ब्रेकडाउन
    -0.47
    rungsseite
    -0.46
     surla
    -0.45
    出版年
    -0.45
    WarningLevel
    -0.42
     severe
    -0.42
    ReusableCell
    -0.42
    createServer
    -0.42
    POSITIVE LOGITS
    CppMethod
    0.44
    Personensuche
    0.41
    assertIn
    0.38
     Disqus
    0.37
    carbo
    0.35
    UrlResolution
    0.35
    reit
    0.34
    FailureListener
    0.34
    ABUL
    0.34
     disambiguazione
    0.33
    Activations Density 0.627%

    No Known Activations