© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 41873
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to tangling and organization of wires

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

    tangle, angle, and entanglement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.69
     للمعارف
    -0.68
     nahilalakip
    -0.65
     désolés
    -0.65
     ControllerBase
    -0.63
    ########.
    -0.63
     kasarigan
    -0.61
    EndGlobalSection
    -0.60
    rungsseite
    -0.59
    RTCK
    -0.59
    POSITIVE LOGITS
     tangle
    1.52
     tangled
    1.49
     entanglement
    1.36
     entangled
    1.27
    anglement
    1.26
    angling
    0.85
    angled
    0.82
    angle
    0.76
     intertw
    0.71
    complicated
    0.70
    Activations Density 0.011%

    No Known Activations