© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 7073
    Prev
    Next
    INDEX
    Explanations

    procedural or enumerated structures in documents

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

    roman numerals used in enumerated lists.

    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
     DPS
    -0.40
     rel
    -0.39
     infor
    -0.38
    Personendaten
    -0.38
    XmlAccessType
    -0.37
     Boh
    -0.36
     facult
    -0.36
     recl
    -0.36
     Bit
    -0.35
     пода
    -0.35
    POSITIVE LOGITS
     ii
    1.21
     iii
    1.09
     vii
    1.04
     viii
    0.98
    ii
    0.96
    iii
    0.93
     iv
    0.92
    viii
    0.90
    vii
    0.89
     ix
    0.83
    Activations Density 0.424%

    No Known Activations