© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 113136
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "screw" and its variations

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

    screw and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    requent
    -0.59
     Infórmanos
    -0.59
    sizeCache
    -0.57
     kasarigan
    -0.57
     Pathfinder
    -0.52
    Aidan
    -0.52
     Lakeland
    -0.51
     Ultima
    -0.51
    hyth
    -0.50
    argout
    -0.50
    POSITIVE LOGITS
     screw
    0.91
    Screw
    0.85
     Screw
    0.84
    screw
    0.79
     screws
    0.76
     Reſ
    0.75
     tornillos
    0.74
     Screws
    0.71
     skru
    0.66
     Inſ
    0.65
    Activations Density 0.006%

    No Known Activations