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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 9390
    Prev
    Next
    INDEX
    Explanations

    references to ice cream and related desserts

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

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    -0.52
    RegressionTest
    -0.49
     collegamento
    -0.41
     tunik
    -0.41
    quelize
    -0.41
     hipote
    -0.40
    HostException
    -0.40
     Gebet
    -0.40
     onFailure
    -0.39
     desmotivaciones
    -0.38
    POSITIVE LOGITS
     ice
    1.42
     Ice
    1.19
     sorbet
    1.14
    Ice
    1.08
     gelato
    1.05
     popsic
    1.05
     frozen
    1.04
    🍦
    1.00
     freezer
    0.98
     icy
    0.95
    Activations Density 0.037%

    No Known Activations