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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 277
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or political discussions about detention and security

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

    Punctuation followed by specific words

    np_acts-logits-general · gemini-2.0-flash

    English words and punctuation

    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
    •Gemma cluster 5

    No Comments

    Negative Logits
     (~
    -0.70
     (&
    -0.68
     (‘
    -0.66
     (
    -0.66
     🙂
    -0.64
    Whilst
    -0.63
     xD
    -0.63
     Whilst
    -0.59
     :)
    -0.59
     fuck
    -0.58
    POSITIVE LOGITS
     isolé
    0.79
     ieri
    0.71
     livré
    0.70
     مرئيه
    0.70
     >>
    0.69
     scattata
    0.69
     VIDEOTAPE
    0.68
     ♪
    0.67
     morire
    0.66
     gruesa
    0.66
    Activations Density 0.026%

    No Known Activations