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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 11192
    Prev
    Next
    INDEX
    Explanations

    phrases related to grooming and personal care

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ありますか
    -0.49
     chops
    -0.48
    ęd
    -0.45
    )_/¯
    -0.44
    oughlin
    -0.42
     distributing
    -0.42
     numériques
    -0.42
     andato
    -0.42
     côtes
    -0.42
    ver
    -0.42
    POSITIVE LOGITS
     Parfum
    0.83
     fragrance
    0.82
     scent
    0.82
    TagMode
    0.79
     Normdatei
    0.77
     perfume
    0.76
     fragrances
    0.74
    UserScript
    0.74
     Scent
    0.73
     scented
    0.73
    Activations Density 0.065%

    No Known Activations