Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114920
    Prev
    Next
    INDEX
    Explanations

    references to cheese in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rptr
    -0.52
    normally
    -0.43
     Rptr
    -0.40
    fml
    -0.39
     Futura
    -0.38
    خواندن
    -0.38
    @_
    -0.37
     normally
    -0.36
     Ror
    -0.36
    )._
    -0.36
    POSITIVE LOGITS
     Cheese
    1.31
     cheese
    1.27
    Cheese
    1.24
    cheese
    1.15
     Chees
    0.93
     cheeses
    0.92
     chees
    0.87
    🧀
    0.82
     Käse
    0.76
    Chees
    0.76
    Activations Density 0.004%

    No Known Activations