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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5655
    Prev
    Next
    INDEX
    Explanations

    keywords and names related to scientific research and technology, particularly in biology and data management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.71
    دانشنامهٔ
    -0.64
     فريبيس
    -0.64
    expandindo
    -0.63
    sidemargin
    -0.63
    AnchorStyles
    -0.62
    الحياه
    -0.61
     AssemblyProduct
    -0.60
    transQ
    -0.57
    Jeografia
    -0.57
    POSITIVE LOGITS
     aleación
    0.32
    ről
    0.32
    contentLoaded
    0.32
    entraînement
    0.32
     menolak
    0.31
     schließlich
    0.31
     păr
    0.31
     také
    0.30
    appui
    0.30
     gelombang
    0.30
    Activations Density 0.939%

    No Known Activations