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. 20-GEMMASCOPE-RES-16K
    6. 12052
    Prev
    Next
    INDEX
    Explanations

    HTML or markup language elements and formatting tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -1.38
     itſelf
    -1.23
     ſeveral
    -1.22
     Efq
    -1.21
     leaſt
    -1.16
     Houſe
    -1.16
    ^(@)
    -1.15
     Diſ
    -1.14
     Theſe
    -1.14
     Anſ
    -1.13
    POSITIVE LOGITS
    <em>
    1.07
    <i>
    0.91
    </em>
    0.90
    <u>
    0.77
    </i>
    0.69
    i
    0.69
    <sup>
    0.64
    ing
    0.63
    s
    0.63
    <code>
    0.62
    Activations Density 0.125%

    No Known Activations