© 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. 13534
    Prev
    Next
    INDEX
    Explanations

    elements related to iconic cultural symbols and institutions

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

    Preceding "classic," "famous," or "successful."

    np_acts-logits-general · gemini-2.0-flash

    classic, famous, standard, iconic

    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
    MigrationBuilder
    -0.97
     виправивши
    -0.95
    DockStyle
    -0.91
    providedIn
    -0.91
    AndEndTag
    -0.91
    脚注の使い方
    -0.88
    RegistryLite
    -0.88
     Normdatei
    -0.86
    tagHelperRunner
    -0.85
     समीक्षक
    -0.84
    POSITIVE LOGITS
     iconic
    1.85
     famous
    1.76
     classic
    1.64
    famous
    1.57
    iconic
    1.50
    classic
    1.44
     classics
    1.44
     legendary
    1.42
     Iconic
    1.41
    Iconic
    1.39
    Activations Density 0.305%

    No Known Activations