© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15489
    Prev
    Next
    INDEX
    Explanations

    concepts related to environmental governance and social dynamics

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

    Sampling or population studies

    np_acts-logits-general · gemini-2.0-flash

    convenience sampling, precautionary approach, relay between

    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
     selezion
    -0.50
    <h1>
    -0.48
    мены
    -0.47
    चना
    -0.46
    łucha
    -0.44
     settled
    -0.44
    ings
    -0.44
    ulations
    -0.43
    ディション
    -0.42
    ments
    -0.41
    POSITIVE LOGITS
     defaultstate
    0.90
    FunctionFlags
    0.84
    LookAnd
    0.83
    contentLoaded
    0.83
     AssemblyCulture
    0.82
    Sucesor
    0.80
    出版年
    0.77
    modelBuilder
    0.77
    matchCondition
    0.76
    IVEREF
    0.75
    Activations Density 1.105%

    No Known Activations