© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15928
    Prev
    Next
    INDEX
    Explanations

    references to temperature, cooling, and air conditioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     farine
    -0.39
     Vikipedi
    -0.37
     مب
    -0.33
     przeds
    -0.32
     intention
    -0.32
    izia
    -0.31
    vertx
    -0.31
     повтор
    -0.31
     nœ
    -0.30
     January
    -0.30
    POSITIVE LOGITS
     cool
    2.86
     Cool
    2.78
    Cool
    2.70
     COOL
    2.55
    cool
    2.55
     cools
    2.41
     coolness
    2.39
    COOL
    2.38
     cooling
    2.36
     cooler
    2.19
    Activations Density 0.115%

    No Known Activations