© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 693
    Prev
    Next
    INDEX
    Explanations

    indicators of legal troubles or criminal activities

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

    driving violations or offenses

    np_acts-logits-general · gemini-2.0-flash

    driving under the influence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.61
    zeera
    -0.57
    HostException
    -0.56
    XtraBars
    -0.56
    ruptedException
    -0.56
     resourceCulture
    -0.54
     iprot
    -0.51
    ValueStyle
    -0.50
    ">//
    -0.47
    AddTagHelper
    -0.47
    POSITIVE LOGITS
     driver
    0.91
     Driver
    0.85
     DUI
    0.83
     Driving
    0.83
     driving
    0.81
     drivers
    0.80
    Driver
    0.80
     Drivers
    0.78
    driver
    0.78
     sobriety
    0.77
    Activations Density 0.195%

    No Known Activations