© 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. 16128
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experience and emotional states

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

    Follows "Q" or is before "less" or a bracket

    np_acts-logits-general · gemini-2.0-flash

    less pain

    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
     Roskov
    -0.89
     متعلقه
    -0.88
     nahilalakip
    -0.74
    новништво
    -0.67
     JAXBElement
    -0.67
    addCriterion
    -0.66
    municipi
    -0.65
    rotz
    -0.65
    Hentet
    -0.63
    ViewFeatures
    -0.62
    POSITIVE LOGITS
     constantly
    0.79
     guilt
    0.76
     compul
    0.72
     constant
    0.72
     self
    0.60
     feeling
    0.59
     perfection
    0.57
     external
    0.57
     incessantly
    0.56
     externally
    0.55
    Activations Density 0.284%

    No Known Activations