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
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9446
    Prev
    Next
    INDEX
    Explanations

    terms related to beer and pubs

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

    the word "beer" and related alcoholic beverage contexts.

    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
    Rapport
    -0.40
    niająca
    -0.37
    PrivateKey
    -0.36
     Violin
    -0.36
     nélkül
    -0.35
     violin
    -0.35
     intim
    -0.34
    Violin
    -0.34
     اح
    -0.34
     Bibliothèque
    -0.33
    POSITIVE LOGITS
     beer
    1.42
     beers
    1.31
     brewery
    1.30
     brewers
    1.24
    Beer
    1.24
     Beer
    1.21
     breweries
    1.20
    beer
    1.18
     brewer
    1.18
     brew
    1.17
    Activations Density 0.065%

    No Known Activations