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. 16105
    Prev
    Next
    INDEX
    Explanations

    references to ice and ice-related products or concepts

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

    "ice" and things associated with it

    np_acts-logits-general · gemini-2.0-flash

    ice and related contexts

    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
     humanidade
    -0.38
     bestuur
    -0.33
    useState
    -0.30
    zustellen
    -0.29
    oulli
    -0.29
    inergic
    -0.28
     maand
    -0.28
    sweise
    -0.28
    zenten
    -0.28
     comunale
    -0.28
    POSITIVE LOGITS
     ice
    0.85
     Ice
    0.81
     ICE
    0.75
    Ice
    0.75
     الحره
    0.71
     Eis
    0.70
     ujednoznacz
    0.69
    Eis
    0.67
    🧊
    0.65
    expandindo
    0.63
    Activations Density 0.043%

    No Known Activations