© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 10784
    Prev
    Next
    INDEX
    Explanations

    references to official sources and insider information regarding political events

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

    attributed statements or quotes from unnamed sources in news reporting.

    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
     समीक्षाएं
    -0.47
     onBackPressed
    -0.44
    findpost
    -0.44
     beginnetje
    -0.42
     ब्रेकडाउन
    -0.42
    новништво
    -0.39
    ContentValues
    -0.39
     Sequelize
    -0.38
    RunWith
    -0.38
    Linki
    -0.37
    POSITIVE LOGITS
     sources
    2.00
     Sources
    1.64
    sources
    1.60
    Sources
    1.55
     source
    1.47
     fuentes
    1.39
     SOURCES
    1.36
     fonti
    1.29
     insiders
    1.27
     fontes
    1.20
    Activations Density 0.186%

    No Known Activations