© 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. 16-GEMMASCOPE-RES-16K
    11. 4647
    Prev
    Next
    INDEX
    Explanations

    queries and questions, particularly those starting with "which" or "what."

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

    Followed by a question/choice

    np_acts-logits-general · gemini-2.0-flash

    which question or selection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     őket
    -0.60
    üben
    -0.55
     betweenstory
    -0.54
     excise
    -0.48
     setempat
    -0.48
     Himself
    -0.48
     correndo
    -0.47
    InstanceState
    -0.47
     rağmen
    -0.47
     jezelf
    -0.47
    POSITIVE LOGITS
    ?')
    0.77
    ?")
    0.75
     Which
    0.73
    ')")
    0.72
    %")
    0.71
    Legături
    0.69
    MergeFrom
    0.69
     version
    0.69
    ']}
    0.68
    ？】
    0.68
    Activations Density 0.125%

    No Known Activations