© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 10802
    Prev
    Next
    INDEX
    Explanations

    references to physical confrontations and violence

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

    Physical attacks or injuries to the head/body

    np_acts-logits-general · gemini-2.0-flash

    striking body parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.50
    WindowConstants
    -0.46
    észetes
    -0.41
    IndentedString
    -0.40
    rrggbb
    -0.38
    Välislingid
    -0.36
     ligiloj
    -0.35
     beginnetje
    -0.35
    ệc
    -0.34
    열
    -0.34
    POSITIVE LOGITS
     forehead
    0.65
     gezicht
    0.58
     cheek
    0.55
     Stirn
    0.53
     face
    0.53
     slapped
    0.49
     squarely
    0.49
    AccessFile
    0.48
    鈍
    0.47
     smacked
    0.47
    Activations Density 0.118%

    No Known Activations