Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3587
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical structures and properties within systems

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

    Mathematical and/or code-related expressions

    np_acts-logits-general · gemini-2.0-flash

    specific mathematical and programming contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    rungsseite
    -0.74
    IsContent
    -0.63
     fubject
    -0.63
     esternos
    -0.60
    multer
    -0.60
    transQ
    -0.59
     ModelExpression
    -0.59
    .*")]
    -0.58
     vastaan
    -0.58
     propOrder
    -0.57
    POSITIVE LOGITS
    ↵↵
    0.31
     Fleisch
    0.29
    ThroughAttribute
    0.28
    }}^{(
    0.27
    pushFollow
    0.27
    Hi
    0.27
    ativement
    0.26
     <=",
    0.25
     dourada
    0.25
    Так
    0.25
    Activations Density 2.735%

    No Known Activations