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. 16155
    Prev
    Next
    INDEX
    Explanations

    terms associated with seafood and culinary experiences

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

    before "enthusiast," "lover," or "fan."

    np_acts-logits-general · gemini-2.0-flash

    people who are fans

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    SourceChecksum
    -0.64
    PreInfinity
    -0.57
    SBATCH
    -0.52
    Хьажоргаш
    -0.50
    ItemBackground
    -0.49
     mxArray
    -0.49
    IVEREF
    -0.47
    дравству
    -0.46
     الحره
    -0.44
    GOTREF
    -0.43
    POSITIVE LOGITS
     enthusiasts
    1.27
     lovers
    1.25
     avid
    1.22
     enthusiast
    1.21
     aficionados
    1.12
     conno
    1.11
     afic
    1.08
     lover
    1.05
     amantes
    1.05
     fans
    0.98
    Activations Density 0.194%

    No Known Activations