© 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. 11266
    Prev
    Next
    INDEX
    Explanations

    Arabic names and titles, particularly those with the prefix "Al."

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

    proper nouns and names, particularly those with hyphens or special formatting.

    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
     InputDecoration
    -0.65
     iprot
    -0.64
    chufe
    -0.60
     CreateTagHelper
    -0.58
    quelize
    -0.57
    epiece
    -0.56
     Numerade
    -0.56
    BibitemShut
    -0.56
    sproz
    -0.54
    Tikang
    -0.53
    POSITIVE LOGITS
     though
    0.31
    xymatrix
    0.30
     BrowserModule
    0.30
    -
    0.30
    SOUNDBITE
    0.29
    sf
    0.29
    ことができました
    0.29
     ku
    0.28
    +][
    0.27
     Standard
    0.26
    Activations Density 0.069%

    No Known Activations