© 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. 21-GEMMASCOPE-RES-16K
    6. 14531
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical compounds and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.60
    upol
    -0.58
     penicillin
    -0.58
     Brandy
    -0.57
     Kaspar
    -0.54
    ///</
    -0.54
     Soledad
    -0.54
     Fulda
    -0.53
     Theſe
    -0.53
    Diwedd
    -0.53
    POSITIVE LOGITS
     Genshin
    0.65
    gens
    0.59
    原神
    0.57
     Hoy
    0.56
     Fisch
    0.56
    ivat
    0.55
    OrNil
    0.55
    魈
    0.54
     rerun
    0.53
     Klee
    0.49
    Activations Density 0.061%

    No Known Activations