© 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. 18-GEMMASCOPE-RES-16K
    11. 4483
    Prev
    Next
    INDEX
    Explanations

    terms related to catalytic reactions and mechanisms

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

    chemical reactions and catalyzed processes

    np_acts-logits-general · gemini-2.0-flash

    exothermic reaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mány
    -0.44
    ProgressHUD
    -0.41
    Acute
    -0.41
     dź
    -0.41
    tryck
    -0.41
    ículos
    -0.40
    ומה
    -0.40
     Travel
    -0.40
    ciąż
    -0.40
     design
    -0.39
    POSITIVE LOGITS
     reactions
    1.42
     reaction
    1.34
     Reactions
    1.25
    Reactions
    1.17
    reactions
    1.16
     Reaction
    1.14
     processes
    1.11
    reaction
    1.11
    Reaction
    1.06
     REACTION
    1.04
    Activations Density 0.945%

    No Known Activations