© 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 - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8692
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the word "dog."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.86
     uſed
    -0.82
     ſeveral
    -0.79
     Dami
    -0.78
     myſelf
    -0.78
     themſelves
    -0.78
     poffible
    -0.75
     reaſon
    -0.74
     Eſ
    -0.73
     neceſſ
    -0.73
    POSITIVE LOGITS
     dog
    3.63
     Dog
    3.43
    Dog
    3.31
    dog
    3.19
     dogs
    3.17
     DOG
    3.05
     Dogs
    2.93
    DOG
    2.69
    Dogs
    2.63
    dogs
    2.61
    Activations Density 0.020%

    No Known Activations