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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6464
    Prev
    Next
    INDEX
    Explanations

    references to biological materials, particularly related to hair and blood

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

    following "hair" or "blood"

    np_acts-logits-general · gemini-2.0-flash

    hair and blood samples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INCREF
    -0.53
     proximity
    -0.52
    maxi
    -0.49
     Maxi
    -0.48
     Vantage
    -0.47
    튿
    -0.47
     occasions
    -0.47
    anera
    -0.47
    例の
    -0.47
     vantage
    -0.47
    POSITIVE LOGITS
    Hair
    0.79
    Blood
    0.75
    Soil
    0.73
     canst
    0.68
    Oil
    0.67
    Fish
    0.67
     Hair
    0.66
    Skin
    0.66
    Milk
    0.66
     hair
    0.65
    Activations Density 0.445%

    No Known Activations