© 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. 18-GEMMASCOPE-RES-16K
    11. 10872
    Prev
    Next
    INDEX
    Explanations

    references to criminal activity and societal issues

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

    before "by", "with", "around"

    np_acts-logits-general · gemini-2.0-flash

    state of being or cessation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.95
    addCriterion
    -0.72
    Попис
    -0.70
     CURIAM
    -0.69
     MenuView
    -0.69
    %;">
    -0.67
    省市镇
    -0.66
     myſelf
    -0.65
    AddHtmlAttribute
    -0.64
    ioutil
    -0.64
    POSITIVE LOGITS
     came
    0.86
     disappeared
    0.83
     became
    0.81
     was
    0.80
     remained
    0.80
     remain
    0.79
     has
    0.77
     vanished
    0.74
     died
    0.73
     went
    0.72
    Activations Density 0.742%

    No Known Activations