© 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. 22-GEMMASCOPE-RES-16K
    11. 2712
    Prev
    Next
    INDEX
    Explanations

    phrases indicating critical moments or turning points in a narrative, particularly in the context of competition or conflict

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

    Tokens after acronyms or abbreviations

    np_acts-logits-general · gemini-2.0-flash

    Ko prefixes and COG identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clarion
    -0.63
     Clarissa
    -0.62
     Denison
    -0.57
    TLR
    -0.56
     Newberry
    -0.56
     TLR
    -0.55
     MPR
    -0.55
     Granville
    -0.55
     Claremont
    -0.55
     Shrewsbury
    -0.54
    POSITIVE LOGITS
     Ko
    1.93
    Ko
    1.85
     CO
    1.75
     ko
    1.74
     Cohen
    1.59
    CO
    1.54
     Ко
    1.49
     코
    1.45
    Ко
    1.42
     Koh
    1.42
    Activations Density 0.468%

    No Known Activations