© 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-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 9936
    Prev
    Next
    INDEX
    Explanations

    references to dogs

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

    the word "dog" in various contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @gulkoa

    the word "dog," especially in contexts discussing the animal itself.

    oai_token-act-pair · gemini-1.5-proTriggered by @gulkoa

    This neuron activates on any occurrence of “dog” (as a standalone word or within compounds), i.e. tokens containing the substring “dog.”

    oai_token-act-pair · o4-miniTriggered by @gulkoa

    the word "dog" and related terms, even when used in disparate contexts ranging from hot dogs to animals.

    oai_token-act-pair · gemini-2.0-flashTriggered by @gulkoa
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.73
     оригіналу
    -0.58
    ($__
    -0.57
     Seeder
    -0.57
     itſelf
    -0.56
     spost
    -0.56
    aarrggbb
    -0.55
    Datuak
    -0.54
     furrow
    -0.54
    voye
    -0.54
    POSITIVE LOGITS
    Dog
    1.27
     dog
    1.27
     Dog
    1.23
    dog
    1.23
     Dogs
    1.10
     DOG
    1.10
    dogs
    1.04
     dogs
    1.00
    DOG
    0.96
    Dogs
    0.95
    Activations Density 0.043%

    No Known Activations