© 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. 314
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss reactions and their associated mixtures or kinetics

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

    chemical "reaction"

    np_acts-logits-general · gemini-2.0-flash

    reaction mixture or time

    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
    Hozzáférés
    -0.61
     كومونز
    -0.60
    CrossRef
    -0.59
     StatelessWidget
    -0.58
    rinfo
    -0.57
    󠁿
    -0.57
    zellan
    -0.57
     defaultstate
    -0.56
     UnityEditor
    -0.56
    Lulu
    -0.55
    POSITIVE LOGITS
     reactions
    1.12
     reacts
    0.98
     Reactions
    0.96
     Reaction
    0.93
    reactions
    0.92
    Reactions
    0.91
    Reaction
    0.90
     react
    0.89
     reaction
    0.89
     reacting
    0.88
    Activations Density 0.128%

    No Known Activations