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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5314
    Prev
    Next
    INDEX
    Explanations

    HTML header tags, indicating sections or important points in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    хьтан
    -0.80
     isInitialized
    -0.78
    peu
    -0.69
     Appel
    -0.68
     الرياضيه
    -0.68
    ípio
    -0.68
     Oskar
    -0.68
    koop
    -0.68
     CORD
    -0.67
    pellier
    -0.67
    POSITIVE LOGITS
    <h3>
    1.78
    <h2>
    1.52
    <h1>
    1.31
    <h5>
    1.14
    <h4>
    1.02
    <strong>
    0.97
    <b>
    0.89
    ])[
    0.81
    <td>
    0.80
    <h6>
    0.79
    Activations Density 0.004%

    No Known Activations