© 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. 18-GEMMASCOPE-RES-16K
    11. 416
    Prev
    Next
    INDEX
    Explanations

    references to cable systems and their components in technical contexts

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

    associated with cables, cords, and ropes

    np_acts-logits-general · gemini-2.0-flash

    cables, cords, lines, ropes, tangling, tension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TargetException
    -0.83
    TacToe
    -0.70
    SuppressMessage
    -0.64
     Pank
    -0.61
     rhinoceros
    -0.59
    ⓧ
    -0.59
    ocino
    -0.58
     lids
    -0.58
     defaultstate
    -0.57
    localctx
    -0.57
    POSITIVE LOGITS
     tension
    1.07
     length
    0.86
     Tension
    0.85
     tensile
    0.83
     string
    0.83
     rope
    0.83
     tensione
    0.82
    Tension
    0.80
     taut
    0.79
    tension
    0.78
    Activations Density 0.468%

    No Known Activations