© 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. 8214
    Prev
    Next
    INDEX
    Explanations

    nouns associated with creative roles or titles

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

    Categories and lists of people

    np_acts-logits-general · gemini-2.0-flash

    Spanish football players

    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
    !”
    -0.82
     ModelExpression
    -0.80
    ,”
    -0.78
    !’
    -0.75
    .’”
    -0.72
    ,’”
    -0.71
    .”
    -0.69
    ,’
    -0.67
    ?”
    -0.67
    ’.”
    -0.67
    POSITIVE LOGITS
    ⓘ
    0.73
     contextLoads
    0.69
    ambiguation
    0.63
    ).[
    0.61
     wikipagina
    0.59
    — 
    0.59
     Wikipedia
    0.58
    ː
    0.56
    ♭
    0.56
     Encyclopædia
    0.56
    Activations Density 1.307%

    No Known Activations