© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 3415
    Prev
    Next
    INDEX
    Explanations

    references to wine and related experiences

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

    the word "wine" and related wine-related content.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
    crollView
    -0.44
     fibro
    -0.40
    ussis
    -0.40
     Administrativna
    -0.38
    ajevo
    -0.37
     Jacinto
    -0.36
    utete
    -0.36
     coser
    -0.36
    óstico
    -0.36
     effective
    -0.36
    POSITIVE LOGITS
     wine
    1.35
     wines
    1.30
     tasting
    1.24
    Wine
    1.13
     Wine
    1.13
     Tasting
    1.02
     Wines
    1.02
    Tasting
    0.99
    tasting
    0.98
     tasted
    0.98
    Activations Density 0.083%

    No Known Activations