© 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. 31848
    Prev
    Next
    INDEX
    Explanations

    references to revenge and associated themes

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

    revenge and vengeance

    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
    slidesToShow
    -0.59
    jsii
    -0.54
    clientHeight
    -0.52
     Normdatei
    -0.49
    KommentareTeilen
    -0.47
    niss
    -0.46
    resizingMask
    -0.46
     Cordillera
    -0.45
    はじめに
    -0.45
    nader
    -0.45
    POSITIVE LOGITS
     venganza
    1.02
     revenge
    1.00
    revenge
    0.86
    Revenge
    0.84
     Revenge
    0.82
     vengeance
    0.72
     avenge
    0.67
    engeance
    0.66
     retaliation
    0.65
    讐
    0.65
    Activations Density 0.015%

    No Known Activations