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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14669
    Prev
    Next
    INDEX
    Explanations

    words and terms related to "mal" as a prefix, indicating something that is harmful or deficient

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

    words starting with Mal

    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
    pidou
    -0.71
    ########.
    -0.69
     Houſe
    -0.65
    InSection
    -0.60
     Anſ
    -0.59
    figsize
    -0.58
    ſelf
    -0.58
    IndentedString
    -0.57
     TextAppearance
    -0.56
    сылкі
    -0.56
    POSITIVE LOGITS
     Mal
    0.89
     MAL
    0.79
     Malone
    0.77
    Mal
    0.76
     Maloney
    0.69
    Malley
    0.68
     Malik
    0.67
     Malcolm
    0.63
     mal
    0.63
     Malvern
    0.62
    Activations Density 0.029%

    No Known Activations