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. 13610
    Prev
    Next
    INDEX
    Explanations

    important aspects and factors related to guidelines or recommendations

    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
    хьтан
    -0.68
     समीक्षक
    -0.62
    zegovina
    -0.60
    RunWith
    -0.59
     türlü
    -0.59
    niss
    -0.58
     Somewhere
    -0.57
     équipé
    -0.57
    ]>=
    -0.56
     ::=
    -0.55
    POSITIVE LOGITS
    styleable
    0.80
    需要注意
    0.80
     worth
    0.73
    要注意
    0.69
     common
    0.67
     you
    0.61
     consideration
    0.61
     to
    0.59
     affecting
    0.58
    值得
    0.56
    Activations Density 0.380%

    No Known Activations