© 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. 17-GEMMASCOPE-RES-16K
    11. 6227
    Prev
    Next
    INDEX
    Explanations

    phrases indicating recognition or acknowledgment of individuals, typically in a context of capability or status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -1.01
     lèvres
    -0.98
     pouvoirs
    -0.95
     épaules
    -0.86
     négociations
    -0.85
     vœux
    -0.85
     démocr
    -0.84
     attentes
    -0.81
     intérêts
    -0.79
     côtés
    -0.79
    POSITIVE LOGITS
     themselves
    1.08
    themselves
    0.91
     những
    0.72
     are
    0.67
     ones
    0.66
     members
    0.62
     mga
    0.60
     veritable
    0.59
     examples
    0.59
     They
    0.56
    Activations Density 0.838%

    No Known Activations