© 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. 12-GEMMASCOPE-RES-16K
    11. 13417
    Prev
    Next
    INDEX
    Explanations

    mentions of "brief" or "quick" descriptions and summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.39
    @[+][
    -0.37
    oredCriteria
    -0.37
    SourceChecksum
    -0.35
     Sicherheits
    -0.32
     eventually
    -0.32
     tro
    -0.32
     bezpieczeństwa
    -0.32
    autorest
    -0.31
     már
    -0.30
    POSITIVE LOGITS
     brief
    1.24
     quick
    1.21
    Brief
    1.17
     Brief
    1.16
    quick
    1.15
    Quick
    1.12
     Quick
    1.12
    brief
    1.06
    QUICK
    1.00
     briefly
    0.97
    Activations Density 0.782%

    No Known Activations