© 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. 9843
    Prev
    Next
    INDEX
    Explanations

    numeric values and their variations or comparisons

    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
     ujednoznacz
    -0.62
    
    -0.60
    RectangleBorder
    -0.55
     فريبيس
    -0.55
     resultCode
    -0.50
     disambiguazione
    -0.48
    protoimpl
    -0.48
     nahilalakip
    -0.45
     Kett
    -0.45
    TestingModule
    -0.45
    POSITIVE LOGITS
    出版年
    0.43
     diría
    0.40
    smarty
    0.39
     pierdas
    0.39
    gång
    0.38
    irut
    0.38
    ſelf
    0.37
     Starr
    0.37
    whip
    0.37
     negó
    0.37
    Activations Density 0.646%

    No Known Activations