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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15963
    Prev
    Next
    INDEX
    Explanations

    references to rescue, saving lives, and themes of support and caring for animals

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

    Saving, rescuing, or avoiding danger

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     clearColor
    -0.45
     ostavi
    -0.44
     Privacidad
    -0.39
    EndProject
    -0.39
     ComVisible
    -0.38
    sizeCache
    -0.38
    يكب
    -0.38
     initComponents
    -0.37
    Спасылкі
    -0.36
    setVerticalGroup
    -0.36
    POSITIVE LOGITS
     rescue
    2.25
     saved
    2.20
     saving
    2.17
     sauver
    2.13
     save
    2.13
     rescuing
    2.08
     salvar
    2.06
     salvare
    2.00
     saves
    2.00
     rescued
    1.97
    Activations Density 0.369%

    No Known Activations