© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 1724
    Prev
    Next
    INDEX
    Explanations

    references to "direction" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abestanden
    -0.92
     
    -0.90
    Espèce
    -0.86
    GEBURTSDATUM
    -0.86
    asantry
    -0.82
    letus
    -0.82
    QMessageBox
    -0.79
    flakes
    -0.79
     NSCoder
    -0.78
     Leal
    -0.78
    POSITIVE LOGITS
     direction
    1.46
     directions
    1.44
     Direction
    1.35
     DIRECTION
    1.34
    Direction
    1.26
    direction
    1.22
    DIRECTION
    1.21
     Directions
    1.21
    directions
    1.19
     DIRECTIONS
    1.11
    Activations Density 0.102%

    No Known Activations