© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 14607
    Prev
    Next
    INDEX
    Explanations

    references to weapons and objects associated with violence

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

    Objects or tools being held or used

    np_acts-logits-general · gemini-2.0-flash

    objects used, often with description

    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
    AddTagHelper
    -0.68
    InitVars
    -0.58
     يتيمه
    -0.50
    Razor
    -0.48
    cshtml
    -0.47
    UVW
    -0.45
     contextLoads
    -0.45
    `,
    -0.44
    denza
    -0.44
     }}"></
    -0.44
    POSITIVE LOGITS
     strapped
    0.52
     clutched
    0.50
     inserted
    0.49
     magique
    0.48
     purchased
    0.47
     puesta
    0.47
     waarmee
    0.46
     used
    0.45
     smuggled
    0.45
     placed
    0.44
    Activations Density 0.654%

    No Known Activations