Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 16200
    Prev
    Next
    INDEX
    Explanations

    references to social issues and their portrayal in news content

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

    sequences indicating continuous time periods or operating durations (like "24 hours a day").

    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
     Trocken
    -0.32
     pescado
    -0.32
     Boven
    -0.29
    towane
    -0.28
    beelding
    -0.28
    uário
    -0.28
     Budaya
    -0.28
     Vogel
    -0.28
    Path
    -0.27
     Mitte
    -0.27
    POSITIVE LOGITS
    NameInMap
    0.86
     clock
    0.82
    AndEndTag
    0.80
     circadian
    0.75
     hours
    0.75
    queryInterface
    0.75
     nonstop
    0.74
     waking
    0.73
     FetchType
    0.72
     CLOCK
    0.71
    Activations Density 0.211%

    No Known Activations