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. 24-GEMMASCOPE-RES-16K
    6. 4542
    Prev
    Next
    INDEX
    Explanations

    terms related to skin lesions and dermatological conditions

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

    Skin, hair, and bodily secretions

    np_acts-logits-general · gemini-2.0-flash

    human skin, saliva, hair, cells

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.75
     Administrativna
    -0.64
    RenderAtEndOf
    -0.56
    verwijspagina
    -0.53
    ografija
    -0.53
    TagMode
    -0.53
    PreferredItem
    -0.53
    AccessorTable
    -0.52
     chi̍t
    -0.52
    RuleContext
    -0.52
    POSITIVE LOGITS
     stratum
    0.69
     corne
    0.68
     keratin
    0.66
     se
    0.66
     epidermal
    0.64
     epidermis
    0.63
     superficial
    0.63
     surface
    0.60
    RectangleBorder
    0.60
    dermal
    0.60
    Activations Density 0.371%

    No Known Activations