© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7093
    Prev
    Next
    INDEX
    Explanations

    expressions of admiration and appreciation

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

    of praise or compliments

    np_acts-logits-general · gemini-2.0-flash

    praise, compliments, and glowing reviews

    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
    Geplaatst
    -0.76
    GEBURTSDATUM
    -0.72
    transQ
    -0.59
    EndInit
    -0.59
     desaf
    -0.55
    .*")]
    -0.54
    Argb
    -0.54
    webElementXpaths
    -0.53
    Grim
    -0.52
     contractions
    -0.52
    POSITIVE LOGITS
     praise
    2.04
     praises
    1.93
     praising
    1.89
     praised
    1.72
     compliments
    1.60
    praise
    1.59
     Praise
    1.58
     compliment
    1.53
    Praise
    1.48
     elog
    1.42
    Activations Density 0.263%

    No Known Activations