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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12792
    Prev
    Next
    INDEX
    Explanations

    phrases related to formal invitations and requests for participation

    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
    Kamu
    -0.46
    mientos
    -0.45
    lage
    -0.41
    erde
    -0.41
    ucht
    -0.40
    alnya
    -0.40
    굿
    -0.39
     world
    -0.39
     onAnimation
    -0.39
    各
    -0.39
    POSITIVE LOGITS
     family
    0.92
     FAMILY
    0.82
     saites
    0.81
    family
    0.81
    URLException
    0.76
    Family
    0.76
     familial
    0.73
     Family
    0.72
     adult
    0.72
    adult
    0.72
    Activations Density 0.283%

    No Known Activations