© 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 EvalsExportsAPI 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. 15004
    Prev
    Next
    INDEX
    Explanations

    requests or inquiries about seeking information or assistance

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

    "ask" or its variations

    np_acts-logits-general · gemini-2.0-flash

    asking or begging

    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
    ingale
    -0.80
     للمعارف
    -0.75
    nodoc
    -0.70
    rotz
    -0.70
    contentLoaded
    -0.70
    saurus
    -0.69
    ]='\
    -0.66
    TextBoxColumn
    -0.66
    derry
    -0.65
    MLLoader
    -0.65
    POSITIVE LOGITS
     ask
    1.11
     asking
    1.04
     asks
    1.01
     ASK
    0.99
     questions
    0.96
     asked
    0.92
     Asking
    0.90
    Asking
    0.90
     Ask
    0.88
    Ask
    0.86
    Activations Density 0.056%

    No Known Activations