© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 132
    Prev
    Next
    INDEX
    Explanations

    identifiers and numeric data in a structured format

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

    individual letters and single characters that appear in text.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tschaft
    -0.54
    ագրություններ
    -0.53
    /**
    -0.52
     detailsNormal
    -0.52
    pend
    -0.52
    Chham
    -0.52
    ContentAsync
    -0.52
     }^{[
    -0.51
    uxxxx
    -0.51
    tvguidetime
    -0.51
    POSITIVE LOGITS
    ientôt
    0.38
    ądź
    0.32
     langsam
    0.32
    GenerationType
    0.31
    imageshack
    0.30
    稳定的
    0.30
     específicamente
    0.29
     gewiß
    0.29
     tačiau
    0.29
     calabaza
    0.29
    Activations Density 1.237%

    No Known Activations