© 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. 3927
    Prev
    Next
    INDEX
    Explanations

    terms related to specific objects or important entities in various contexts, such as literary works and events

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

    ending in "side", "point", or "time"

    np_acts-logits-general · gemini-2.0-flash

    location and perspective

    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
    k
    -0.67
    e
    -0.63
    ar
    -0.61
    i
    -0.59
     }{@
    -0.59
    b
    -0.57
    bo
    -0.57
    -
    -0.57
    us
    -0.56
    E
    -0.56
    POSITIVE LOGITS
     doubtnut
    0.86
    citenamefont
    0.84
     betweenstory
    0.83
     themſelves
    0.81
    BibitemShut
    0.81
    bibinfo
    0.80
     ་་
    0.79
    ADRID
    0.77
     faſt
    0.77
     ―――――
    0.75
    Activations Density 1.234%

    No Known Activations