© 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. 4052
    Prev
    Next
    INDEX
    Explanations

    temporal markers or phrases indicating time or sequence

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

    Prepositions and words that act like prepositions

    np_acts-logits-general · gemini-2.0-flash

    preposition followed by action or state

    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
     Normdatei
    -0.70
    uxxxx
    -0.70
    ".
    -0.65
    %.
    -0.57
     <>",
    -0.57
    ™.
    -0.57
    」。
    -0.56
    principalColumn
    -0.56
    ...".
    -0.56
    InsertCommand
    -0.56
    POSITIVE LOGITS
    findpost
    0.70
     demikian
    0.64
     للاسماء
    0.64
     these
    0.62
     الحره
    0.59
     vậy
    0.59
    hogy
    0.58
    xious
    0.58
     समीक्षाओं
    0.57
    ParallelGroup
    0.57
    Activations Density 0.669%

    No Known Activations