© 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. 38-GEMMASCOPE-RES-16K
    11. 8230
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as templates, classes, and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Annahme
    -0.42
     composición
    -0.40
     Vereinbarung
    -0.39
     imaginación
    -0.37
     izdel
    -0.36
     Verpflichtung
    -0.36
     übrigen
    -0.36
     embarazada
    -0.36
     Zusammenarbeit
    -0.36
     Jungen
    -0.36
    POSITIVE LOGITS
     Zu
    0.62
    Билгалдахарш
    0.59
     Tur
    0.59
     ſta
    0.57
    endphp
    0.56
     Ric
    0.56
     Tet
    0.56
     utafitiHapana
    0.56
     EconPapers
    0.56
     fili
    0.55
    Activations Density 1.198%

    No Known Activations