© 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. 15944
    Prev
    Next
    INDEX
    Explanations

    direct discourse and questions within dialogue

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

    Follows a statement or answer

    np_acts-logits-general · gemini-2.0-flash

    Yes/No/indeed

    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
    __':
    -1.02
     '\\;'
    -0.98
    __":
    -0.95
    ']):
    -0.86
    ⓧ
    -0.84
     jScrollPane
    -0.84
    WriteTagHelper
    -0.83
    ftagPool
    -0.82
     Paglinawan
    -0.82
    })();
    -0.82
    POSITIVE LOGITS
    !
    0.69
    .
    0.52
    ,
    0.52
    Indeed
    0.52
    –
    0.49
    —
    0.48
     novios
    0.46
    ..
    0.46
     indeed
    0.45
    baiki
    0.45
    Activations Density 0.188%

    No Known Activations