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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7326
    Prev
    Next
    INDEX
    Explanations

    structural elements and metadata related to code documentation and licensing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Signalez
    -0.82
     Taktlose
    -0.74
     يتيمه
    -0.74
    RenderAtEndOf
    -0.73
    oredCriteria
    -0.72
    ReusableCell
    -0.63
     snippetHide
    -0.63
    MessageOf
    -0.63
    vician
    -0.60
     <>",
    -0.60
    POSITIVE LOGITS
    ()]);
    0.35
    ↵↵↵↵↵
    0.35
    ']));
    0.34
    ↵↵↵
    0.34
    ()])
    0.33
    ″]
    0.33
    UNUSED
    0.32
     •
    0.32
    shtml
    0.32
     half
    0.31
    Activations Density 0.759%

    No Known Activations