© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13346
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings or states of being

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

    Adjectives after intensifiers (most, very, really)

    np_acts-logits-general · gemini-2.0-flash

    states of feeling or ability

    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
     péri
    -0.69
     isNameExpr
    -0.60
     Eſ
    -0.60
     ressemb
    -0.60
    cresc
    -0.58
     Explained
    -0.58
     comigo
    -0.58
     stammen
    -0.58
     rând
    -0.57
     industriale
    -0.57
    POSITIVE LOGITS
     aware
    1.50
     interested
    1.47
     willing
    1.32
     able
    1.28
     afraid
    1.27
     addicted
    1.18
     confident
    1.18
     pleased
    1.16
     excited
    1.16
     obsessed
    1.15
    Activations Density 1.331%

    No Known Activations