© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 92521
    Prev
    Next
    INDEX
    Explanations

    instances of the word "convicted" and related terms associated with criminal convictions

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

    convicted or conviction

    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
    Else
    -0.54
    쉬
    -0.50
    resources
    -0.46
    Zee
    -0.45
    pear
    -0.45
    Air
    -0.45
    źródło
    -0.44
    Nada
    -0.44
    lings
    -0.44
    seemed
    -0.43
    POSITIVE LOGITS
     conviction
    0.94
     convictions
    0.90
     convicted
    0.84
     Conv
    0.74
     convict
    0.73
     convic
    0.69
     onCancelled
    0.67
    Conv
    0.65
    conv
    0.65
     AssemblyTitle
    0.63
    Activations Density 0.017%

    No Known Activations