© 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 - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 67
    Prev
    Next
    INDEX
    Explanations

    references to dogs and playful behavior in the context of pets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endblock
    -0.68
     geslacht
    -0.56
    matchCondition
    -0.53
    izarse
    -0.49
    ktop
    -0.49
     Staying
    -0.49
     blijven
    -0.48
     []:
    -0.47
     griega
    -0.46
     służ
    -0.46
    POSITIVE LOGITS
     care
    0.87
     bounding
    0.82
     sau
    0.81
     tr
    0.81
    Care
    0.80
     barre
    0.79
     hurt
    0.78
     lumber
    0.77
     sca
    0.76
     Care
    0.76
    Activations Density 0.317%

    No Known Activations