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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 65028
    Prev
    Next
    INDEX
    Explanations

    image-related elements and attributes in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    img html tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    SBATCH
    -0.66
    ỏa
    -0.60
    ſelves
    -0.59
     विश्वसनीयता
    -0.59
    wpi
    -0.58
    onien
    -0.58
     plaît
    -0.57
    RTHOOK
    -0.57
    few
    -0.56
    </tfoot>
    -0.56
    POSITIVE LOGITS
     img
    1.13
    img
    1.06
    Img
    1.02
     Img
    0.91
     IMG
    0.83
    IMG
    0.79
     imgs
    0.77
    imgUrl
    0.76
    imgs
    0.73
    Imgs
    0.68
    Activations Density 0.004%

    No Known Activations