© 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. 20-GEMMASCOPE-RES-16K
    11. 3944
    Prev
    Next
    INDEX
    Explanations

    news announcements or declarations related to actions taken or events

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

    Follows "announced" and precedes associated details

    np_acts-logits-general · gemini-2.0-flash

    announced plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -1.00
    etheless
    -0.87
    PerformLayout
    -0.79
    MigrationBuilder
    -0.79
     Wiktionnaire
    -0.77
    \{\\
    -0.76
    Referanser
    -0.69
    Either
    -0.68
    sizeCache
    -0.68
     vaikka
    -0.65
    POSITIVE LOGITS
     plans
    0.86
     two
    0.82
     new
    0.73
    新たに
    0.73
     three
    0.70
     four
    0.67
     oficialmente
    0.67
     preliminary
    0.63
    plans
    0.63
     five
    0.63
    Activations Density 0.364%

    No Known Activations