© 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. 37-GEMMASCOPE-RES-16K
    6. 4336
    Prev
    Next
    INDEX
    Explanations

    references to cheese and cheese-related dishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incomplète
    -0.54
    WithIOException
    -0.50
     Khartoum
    -0.50
    Източници
    -0.49
     Beagle
    -0.48
    jsxFileName
    -0.48
     архивлан
    -0.47
     propOrder
    -0.45
    bootstrapcdn
    -0.45
    keyframes
    -0.44
    POSITIVE LOGITS
     cheese
    1.64
     Cheese
    1.38
     cheeses
    1.31
    cheese
    1.30
    Cheese
    1.28
    🧀
    1.16
     cheddar
    1.13
     Käse
    1.13
    チーズ
    1.07
     Cheddar
    1.02
    Activations Density 0.218%

    No Known Activations