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. 5-GEMMASCOPE-RES-16K
    6. 2579
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific processes and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MathML
    -0.57
    ochond
    -0.49
    glEnd
    -0.46
     ca
    -0.46
     P
    -0.45
     W
    -0.44
     S
    -0.44
     modern
    -0.44
     C
    -0.43
     H
    -0.42
    POSITIVE LOGITS
     Roskov
    1.06
    vician
    0.84
     ivelany
    0.83
    mybatisplus
    0.80
    bootstrapcdn
    0.79
    цездатний
    0.78
    Hentet
    0.77
     himo
    0.76
    Jeografia
    0.76
    luiting
    0.74
    Activations Density 3.987%

    No Known Activations