© 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. 17-GEMMASCOPE-RES-16K
    11. 10293
    Prev
    Next
    INDEX
    Explanations

    instances of reporting speech or claims attributed to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    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
    -0.83
     EconPapers
    -0.76
     /></
    -0.67
    expandindo
    -0.64
    AndEndTag
    -0.63
     AssemblyCulture
    -0.62
    /></
    -0.62
     kasarigan
    -0.62
     says
    -0.59
    >-->
    -0.57
    POSITIVE LOGITS
     referring
    0.95
     refiri
    0.93
     referencing
    0.66
     rifer
    0.62
     about
    0.57
     Referring
    0.55
    Referring
    0.54
    Referències
    0.54
     quoting
    0.53
    refer
    0.52
    Activations Density 0.239%

    No Known Activations