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. 23-GEMMASCOPE-RES-16K
    6. 7597
    Prev
    Next
    INDEX
    Explanations

    academic institutions and their associated departments or research areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.54
    viaf
    -0.54
    出版年
    -0.54
    vuo
    -0.50
    cshtml
    -0.49
    huff
    -0.48
    getWriter
    -0.46
     ***!
    -0.46
     Forscher
    -0.45
    bootstrapcdn
    -0.45
    POSITIVE LOGITS
     physiology
    0.98
     sociology
    0.96
     biology
    0.96
     biochemistry
    0.92
     ecology
    0.91
     physics
    0.91
     botany
    0.91
     genetics
    0.90
     microbiology
    0.89
     psychology
    0.89
    Activations Density 0.646%

    No Known Activations