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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10871
    Prev
    Next
    INDEX
    Explanations

    instances of purchasing or acquiring food and beverages

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

    phrases describing beverages and drinks consumed in social or leisure settings.

    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
     bakter
    -0.38
    หน
    -0.37
    vegli
    -0.37
    ztus
    -0.36
    Erreferentziak
    -0.35
    WebpackPlugin
    -0.35
    ดิ
    -0.34
     הה
    -0.34
     relógio
    -0.34
     وص
    -0.33
    POSITIVE LOGITS
     drink
    1.47
     drinks
    1.46
     cup
    1.46
     beer
    1.43
     coffee
    1.40
     beers
    1.38
     beverage
    1.34
     cups
    1.28
     beverages
    1.23
     wine
    1.19
    Activations Density 0.214%

    No Known Activations