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. 2272
    Prev
    Next
    INDEX
    Explanations

    terms related to Samoan culture and spirituality

    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
     consultato
    -0.65
     pse
    -0.63
    ۪
    -0.63
     CANADIAN
    -0.62
     Malaysian
    -0.61
     Canadian
    -0.60
     Majefty
    -0.60
     Serp
    -0.60
     Anſ
    -0.60
     itſelf
    -0.59
    POSITIVE LOGITS
    HttpConnection
    0.50
    Getenv
    0.48
    ⓧ
    0.48
     combineReducers
    0.47
    OkHttpClient
    0.46
    TagMode
    0.46
    GOTREF
    0.46
     milliards
    0.45
    StringVar
    0.45
    AndEndTag
    0.45
    Activations Density 0.015%

    No Known Activations