© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 20-GEMMASCOPE-RES-16K
    11. 11896
    Prev
    Next
    INDEX
    Explanations

    statements of personal expression and experiences

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

    First person pronouns followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    I want, I can, I know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     already
    -0.63
     Already
    -0.58
     quoque
    -0.56
    already
    -0.55
    Already
    -0.54
     also
    -0.53
     právě
    -0.53
     springfox
    -0.53
     juist
    -0.52
    Xna
    -0.51
    POSITIVE LOGITS
     ever
    1.09
     EVER
    0.87
     really
    0.80
     Really
    0.80
    Really
    0.77
     realmente
    0.74
     tartalomajánló
    0.73
     véritable
    0.72
    really
    0.72
     wirklich
    0.71
    Activations Density 0.190%

    No Known Activations