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. 4239
    Prev
    Next
    INDEX
    Explanations

    terms related to social issues and urban environments

    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
    PMailer
    -0.67
    Välislingid
    -0.63
    HttpEntity
    -0.59
     Whigs
    -0.56
    ModelAttribute
    -0.56
    processData
    -0.51
     Mérida
    -0.51
    witzerland
    -0.51
    bietern
    -0.50
    ậc
    -0.49
    POSITIVE LOGITS
    IVEREF
    0.72
     كومونز
    0.68
     gang
    0.67
    ()];
    0.64
    liferay
    0.63
    xase
    0.63
    ]";
    0.62
     gangs
    0.62
    )))));
    0.61
    %");
    0.61
    Activations Density 0.427%

    No Known Activations