© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29236
    Prev
    Next
    INDEX
    Explanations

    fragments and convoluted phrases within discussions about attributes or assessments of engineering and cultural topics

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

    incorrect or nope

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    <bos>
    -0.57
    ніципа
    -0.50
     altında
    -0.45
    spaceBetween
    -0.45
    GeneratedMessage
    -0.44
     defaultstate
    -0.44
    aspectj
    -0.41
    OrBuilder
    -0.40
    mappedBy
    -0.40
    restes
    -0.39
    POSITIVE LOGITS
     WRONG
    1.25
     wrong
    1.20
    wrong
    1.14
     Wrong
    1.14
    WRONG
    1.10
     Nope
    1.04
    Wrong
    1.04
    nope
    0.98
     incorrect
    0.94
     nope
    0.93
    Activations Density 0.242%

    No Known Activations