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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 5320
    Prev
    Next
    INDEX
    Explanations

    references to coffee and related food items

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

    the word "coffee" in various 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
    føring
    -0.37
     AssemblyTitle
    -0.34
    inher
    -0.34
    __',
    -0.34
     montanha
    -0.34
     fuite
    -0.34
     Normdatei
    -0.33
     profondità
    -0.33
     vantagem
    -0.33
     abordagem
    -0.32
    POSITIVE LOGITS
     виправивши
    0.69
    PyExc
    0.63
     sauce
    0.57
    WireFormatLite
    0.55
     Sauce
    0.55
    bread
    0.54
     BREAD
    0.54
     barrel
    0.52
    Sauce
    0.52
     ContentValues
    0.52
    Activations Density 0.421%

    No Known Activations