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. 2473
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation and special characters, specifically periods and parentheses

    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
     
    -0.56
     in
    -0.53
    ment
    -0.51
     fram
    -0.51
    2
    -0.50
    5
    -0.49
    ավ
    -0.47
    (
    -0.47
     opp
    -0.47
    ————————————————
    -0.46
    POSITIVE LOGITS
     resourceCulture
    1.14
    $.}
    1.13
    '].'
    1.06
     kasarigan
    1.05
    __).
    1.02
    ()].
    0.97
     `.
    0.96
     للمعارف
    0.96
    ).}
    0.94
    ⓧ
    0.94
    Activations Density 0.939%

    No Known Activations