© 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-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 10010
    Prev
    Next
    INDEX
    Explanations

    references to dogs and rabbits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Хьажоргаш
    -0.81
    fjspx
    -0.79
    fromCharCode
    -0.78
     nahilalakip
    -0.72
     snippetHide
    -0.71
     unknownFields
    -0.68
     chi̍t
    -0.66
    ByExample
    -0.66
    Manbalar
    -0.65
    NewUrlParser
    -0.65
    POSITIVE LOGITS
     Dog
    1.16
     Dogs
    1.08
    Dog
    1.04
     puppy
    1.03
    Dogs
    0.96
     dogs
    0.96
     DOG
    0.95
     dog
    0.94
    dog
    0.94
     Puppy
    0.88
    Activations Density 0.032%

    No Known Activations