© 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. 970
    Prev
    Next
    INDEX
    Explanations

    phrases related to the conclusion or end of events

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

    "end of"

    np_acts-logits-general · gemini-2.0-flash

    end of

    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
     Insee
    -0.66
    NameInMap
    -0.60
     муніципалі
    -0.55
     CanadaChoose
    -0.54
    MessageOf
    -0.53
    #+#
    -0.53
    matica
    -0.52
    tudiant
    -0.51
     wireType
    -0.51
    Olvid
    -0.51
    POSITIVE LOGITS
     estekak
    0.74
     مشين
    0.67
    conio
    0.66
     duquel
    0.63
    enumi
    0.56
    脚注の使い方
    0.53
     otomatig
    0.53
     հղումներ
    0.52
    Portail
    0.52
    aarrggbb
    0.47
    Activations Density 0.114%

    No Known Activations