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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 13222
    Prev
    Next
    INDEX
    Explanations

    the use of examples and illustrative cases in discussions or analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 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
    unque
    -0.55
    stagland
    -0.53
    berdayakan
    -0.52
     raisonnable
    -0.52
    twimg
    -0.51
     légère
    -0.50
     Normdatei
    -0.48
    WebServlet
    -0.47
    WEBPACK
    -0.47
    XMLSchema
    -0.47
    POSITIVE LOGITS
     example
    1.23
     examples
    1.22
     Beispiele
    1.11
    exemple
    1.11
    examples
    1.08
     Examples
    1.05
     Example
    1.04
     exemples
    1.02
    Examples
    0.99
    Example
    0.98
    Activations Density 0.420%

    No Known Activations