© 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. 15-GEMMASCOPE-RES-16K
    11. 3161
    Prev
    Next
    INDEX
    Explanations

    corporate announcements and press releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.84
    GraphicsUnit
    -0.82
     referrerpolicy
    -0.78
     <<<<<<<<<<<<<<
    -0.75
    \{\\
    -0.75
    devamını
    -0.73
    脚注の使い方
    -0.73
    enderror
    -0.71
    principalColumn
    -0.71
     Efq
    -0.70
    POSITIVE LOGITS
    新たに
    0.59
    AlterField
    0.52
     new
    0.52
    を追加
    0.51
    新しい
    0.48
    新しく
    0.48
    new
    0.47
     formally
    0.47
    新的
    0.45
     registered
    0.45
    Activations Density 0.278%

    No Known Activations