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. 13260
    Prev
    Next
    INDEX
    Explanations

    bold or emphasized formatting elements in the text

    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
    expandindo
    -1.35
    MigrationBuilder
    -0.91
    AllAfrica
    -0.90
    verwijspagina
    -0.90
     AssemblyVersion
    -0.86
     ویکی‌پدی
    -0.84
    IntoConstraints
    -0.83
    InjectAttribute
    -0.83
     BoxDecoration
    -0.83
     <>",
    -0.81
    POSITIVE LOGITS
    <em>
    0.64
    <strong>
    0.60
    <u>
    0.59
    <b>
    0.57
    </strong>
    0.54
     positively
    0.48
    textbf
    0.47
    :
    0.47
    <i>
    0.46
    “
    0.46
    Activations Density 0.185%

    No Known Activations