© 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. 22-GEMMASCOPE-RES-16K
    11. 11321
    Prev
    Next
    INDEX
    Explanations

    references to wiring and cable technology

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

    "wire" or "cable"

    np_acts-logits-general · gemini-2.0-flash

    wire and cable applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.76
     Majefty
    -0.75
     <>",
    -0.70
    abestanden
    -0.69
     pleaſure
    -0.69
     Monfieur
    -0.67
    OrWhiteSpace
    -0.66
     myſelf
    -0.65
     juſt
    -0.64
     Menor
    -0.64
    POSITIVE LOGITS
     cutters
    0.53
     lengths
    0.52
     running
    0.52
     colspan
    0.52
    mesh
    0.51
    work
    0.51
     length
    0.50
    lessly
    0.50
     mesh
    0.50
    line
    0.49
    Activations Density 0.299%

    No Known Activations