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. 15-GEMMASCOPE-RES-16K
    6. 2859
    Prev
    Next
    INDEX
    Explanations

    terms and conditions related to skin health and disease

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nunn
    -0.67
    CodedInputStream
    -0.66
    poved
    -0.64
    sop
    -0.63
    āv
    -0.62
     Mello
    -0.62
     Haddad
    -0.61
    lified
    -0.60
    setAge
    -0.60
     Dado
    -0.59
    POSITIVE LOGITS
     skin
    1.57
     Skin
    1.53
    Skin
    1.53
     SKIN
    1.49
     skins
    1.41
    skin
    1.38
    SKIN
    1.37
     peau
    1.21
     Skins
    1.17
     skinned
    1.15
    Activations Density 0.133%

    No Known Activations