© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 6205
    Prev
    Next
    INDEX
    Explanations

    historical references to military events or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.49
     surla
    -0.46
     plancher
    -0.40
     floor
    -0.36
     valmis
    -0.36
     tendência
    -0.35
    UnusedPrivate
    -0.35
    mesin
    -0.35
     Ganzen
    -0.35
    getMinutes
    -0.35
    POSITIVE LOGITS
     Travel
    0.65
     travel
    0.62
    Демографія
    0.56
     Trekking
    0.56
    travel
    0.55
     trekking
    0.54
    RegressionTest
    0.54
     travels
    0.54
     travellers
    0.53
     travelling
    0.53
    Activations Density 0.507%

    No Known Activations