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. 15764
    Prev
    Next
    INDEX
    Explanations

    mentions of ice cream in various contexts

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

    Ice cream and frozen desserts

    np_acts-logits-general · gemini-2.0-flash

    ice cream and frozen desserts

    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
     Normdatei
    -0.47
     dependencia
    -0.45
     perang
    -0.41
     Hongrie
    -0.40
     commento
    -0.40
     règne
    -0.39
     amitié
    -0.39
     pétrole
    -0.39
     hipote
    -0.38
     avião
    -0.38
    POSITIVE LOGITS
     ice
    1.34
     Ice
    1.10
     gelato
    1.08
    🍦
    1.02
     sorbet
    1.01
    Ice
    0.97
     scoops
    0.90
    冰淇淋
    0.90
     helado
    0.90
    icec
    0.90
    Activations Density 0.040%

    No Known Activations