© 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. 8171
    Prev
    Next
    INDEX
    Explanations

    rankings and lists of top institutions or entities in various contexts

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

    superlative rankings and top lists (phrases like "top ten," "top 100," etc.).

    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
    GOTREF
    -0.50
    EndContext
    -0.47
    verwijspagina
    -0.46
    ByVersion
    -0.46
    oulos
    -0.42
    EndGlobalSection
    -0.41
    vician
    -0.41
    esModule
    -0.41
    ollectionView
    -0.40
    aarrggbb
    -0.39
    POSITIVE LOGITS
     top
    2.34
     Top
    2.19
    Top
    2.03
     TOP
    1.87
    top
    1.80
    TOP
    1.77
    getTop
    1.47
    トップ
    1.41
     टॉप
    1.40
     топ
    1.38
    Activations Density 0.312%

    No Known Activations