© 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. 8646
    Prev
    Next
    INDEX
    Explanations

    phrases related to chemical properties and analysis

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

    figure captions and descriptions in scientific papers, including images, graphs, and diagrams with their explanatory text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
     Houſe
    -0.77
     Theſe
    -0.74
     myſelf
    -0.74
     Reſ
    -0.71
     uſe
    -0.70
     pleaſure
    -0.69
     Monfieur
    -0.69
     houſe
    -0.68
    oredCriteria
    -0.66
     purpoſe
    -0.66
    POSITIVE LOGITS
     example
    0.39
     Example
    0.38
    Example
    0.36
    UnusedPrivate
    0.35
     (
    0.34
    renderItem
    0.32
    mitglied
    0.31
    耀
    0.31
     responses
    0.31
     leading
    0.31
    Activations Density 0.717%

    No Known Activations