© 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. 253
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names, particularly in legal or formal contexts

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

    Short, uncommon character sequences

    np_acts-logits-general · gemini-2.0-flash

    news, rumors, marsh

    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
     AssemblyCulture
    -0.96
    Portály
    -0.95
    Espèce
    -0.93
    EDEFAULT
    -0.93
     ویکی‌پدیا
    -0.92
    amemnon
    -0.91
    IndentedString
    -0.89
    ousand
    -0.89
    FieldBuilder
    -0.85
    VIAF
    -0.85
    POSITIVE LOGITS
    il
    0.63
    te
    0.61
    ta
    0.61
    ka
    0.59
    z
    0.58
    é
    0.57
    ir
    0.56
    á
    0.56
    k
    0.56
    im
    0.56
    Activations Density 0.702%

    No Known Activations