© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3839
    Prev
    Next
    INDEX
    Explanations

    terms related to medical and technical processes

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

    computer programming and technical documentation terms.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
     république
    -0.55
    <bos>
    -0.55
     dieux
    -0.52
     húmedo
    -0.51
     fièvre
    -0.48
     femelle
    -0.47
    Và
    -0.46
     hidrá
    -0.46
     Púb
    -0.45
    List
    -0.44
    POSITIVE LOGITS
    ation
    1.02
    alisation
    1.02
    ization
    0.99
    cination
    0.98
    itation
    0.97
    iration
    0.94
    tration
    0.93
    mation
    0.93
    stration
    0.93
    isation
    0.91
    Activations Density 1.235%

    No Known Activations