© 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. 20-GEMMASCOPE-RES-16K
    11. 16310
    Prev
    Next
    INDEX
    Explanations

    code snippets related to object creation and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yanlış
    -0.36
    GameData
    -0.35
     Peraturan
    -0.35
     invierno
    -0.34
     národ
    -0.34
     esquí
    -0.33
     garantías
    -0.32
     pää
    -0.32
     étroite
    -0.32
     yalnız
    -0.32
    POSITIVE LOGITS
    StoryboardSegue
    0.85
    ReusableCell
    0.73
     newInstance
    0.68
    createNewFile
    0.66
    Autoritní
    0.66
    RTGC
    0.65
    WithIOException
    0.65
     autorytatywna
    0.65
    ValueGenerated
    0.63
     createSprite
    0.63
    Activations Density 0.225%

    No Known Activations