© 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. 8982
    Prev
    Next
    INDEX
    Explanations

    contextual references pertaining to distance, movement, or spatial relationships.

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

    phrases related to distance and spatial relationships.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    definitions or explanations of terms, especially when introduced with phrases like "defines as" or followed by a colon and explanation.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    following prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    then harvested, move or go

    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
    aarrggbb
    -0.80
    Tikang
    -0.77
     ProtoMessage
    -0.74
     kasarigan
    -0.71
    存于互联网档案馆
    -0.71
    AccessorTable
    -0.70
    principalTable
    -0.70
    AndEndTag
    -0.69
     Réponses
    -0.69
     مرئيه
    -0.68
    POSITIVE LOGITS
     something
    0.78
     someone
    0.73
     sth
    0.66
    something
    0.62
     especially
    0.60
    Something
    0.60
    하다
    0.60
    someone
    0.59
     чого
    0.59
     oneself
    0.58
    Activations Density 0.192%

    No Known Activations