Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 1887
    Prev
    Next
    INDEX
    Explanations

    HTML opening and closing tags in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.89
    jsxFileName
    -0.61
    rungsseite
    -0.57
    uxxxx
    -0.55
    verifyException
    -0.51
     Ey
    -0.51
    cyjny
    -0.49
     offered
    -0.49
    כת
    -0.48
    ########.
    -0.48
    POSITIVE LOGITS
    br
    0.89
    BR
    0.68
    Br
    0.67
     br
    0.62
    script
    0.60
    hr
    0.60
    input
    0.59
     ModelExpression
    0.56
    SCRIPT
    0.52
    form
    0.51
    Activations Density 0.088%

    No Known Activations