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
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16243
    Prev
    Next
    INDEX
    Explanations

    references to Wiccan practices and festivals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    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
    AnchorStyles
    -0.64
    StoryboardSegue
    -0.55
    onnaise
    -0.54
    craper
    -0.53
     Nop
    -0.53
    исленность
    -0.52
     zebra
    -0.51
    addContainerGap
    -0.51
     wireType
    -0.50
    HomeAsUpEnabled
    -0.50
    POSITIVE LOGITS
     spell
    1.08
     witchcraft
    1.08
     witch
    1.08
     spells
    1.05
     witches
    1.02
     Witch
    1.01
     Witches
    0.93
    Witch
    0.92
     magic
    0.88
     Spells
    0.85
    Activations Density 0.286%

    No Known Activations