© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14404
    Prev
    Next
    INDEX
    Explanations

    content related to villains and antagonistic characters

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

    Follows nouns related to misfortune or opposition

    np_acts-logits-general · gemini-2.0-flash

    treasure, threat, evil entities

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     okuyayım
    -0.47
    FieldNumber
    -0.43
    createServer
    -0.42
    AISSEE
    -0.41
    PDOException
    -0.39
    nologue
    -0.37
    AutoModerator
    -0.37
    XmlAccessType
    -0.36
    featureID
    -0.36
    initializeApp
    -0.36
    POSITIVE LOGITS
     culprit
    0.43
     culprits
    0.41
    makeatletter
    0.41
    ară
    0.41
    cul
    0.41
     dAtA
    0.39
    大利
    0.39
     hq
    0.39
    laut
    0.39
     culminated
    0.39
    Activations Density 0.297%

    No Known Activations