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

    Neuronpedia

    APICircuit 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. 3-GEMMASCOPE-RES-16K
    6. 11237
    Prev
    Next
    INDEX
    Explanations

    HTML header tags (h2, h3, h4) 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 @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    İstinadlar
    -0.62
    ing
    -0.60
     فريبيس
    -0.57
    LLocation
    -0.57
    bootstrapcdn
    -0.56
     Emits
    -0.53
     Morley
    -0.52
     bolt
    -0.51
    latLng
    -0.51
     hashCode
    -0.51
    POSITIVE LOGITS
    <h3>
    2.52
    <h4>
    2.26
    <h2>
    2.22
    <h5>
    2.21
    <h6>
    1.84
    <h1>
    1.73
    <th>
    1.22
    <strong>
    1.15
    <table>
    1.07
    /*
    1.02
    Activations Density 0.019%

    No Known Activations