© 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 EvalsExportsinterp-engineNEWAPI 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. 30480
    Prev
    Next
    INDEX
    Explanations

    punctuation and certain structural elements of text

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

    similarity and comparison

    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
     ModelExpression
    -0.47
    ToRefresh
    -0.46
    पया
    -0.44
     пад
    -0.43
    čić
    -0.43
    屁
    -0.41
     č
    -0.41
    argmin
    -0.40
     przy
    -0.40
    Życiorys
    -0.40
    POSITIVE LOGITS
    Similarly
    2.36
     Similarly
    2.34
     similarly
    2.23
    Likewise
    2.20
     Likewise
    2.16
    same
    2.05
     same
    2.02
    Same
    1.98
     likewise
    1.95
     Same
    1.82
    Activations Density 0.570%

    No Known Activations