© 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. 2151
    Prev
    Next
    INDEX
    Explanations

    phrases related to making correct decisions or choices

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

    correct or appropriate actions/methods

    np_acts-logits-general · gemini-2.0-flash

    the right thing

    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
    SequentialGroup
    -0.69
    GEBURTSDATUM
    -0.63
     OFDb
    -0.62
     виправивши
    -0.60
     Wiktionnaire
    -0.58
     transférez
    -0.58
    ItemLayout
    -0.57
    gameserver
    -0.57
    ferrer
    -0.56
    titleMargin
    -0.53
    POSITIVE LOGITS
     kind
    1.00
     kinds
    0.93
     sort
    0.82
     thing
    0.79
     amount
    0.76
     sorts
    0.74
     type
    0.73
     types
    0.71
    kind
    0.63
     mix
    0.63
    Activations Density 0.175%

    No Known Activations