© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11974
    Prev
    Next
    INDEX
    Explanations

    numerical or quantitative expressions related to various subjects

    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
    untamente
    -0.48
     AssemblyTitle
    -0.47
     Bewußt
    -0.46
    chriften
    -0.44
     hidupnya
    -0.44
    最快更新
    -0.43
    iço
    -0.43
     Vordergrund
    -0.42
    AttributeValue
    -0.42
     varandra
    -0.42
    POSITIVE LOGITS
     ویکی‌پدی
    0.47
     CreateTagHelper
    0.43
    CloseOperation
    0.42
     transfieras
    0.38
    RUnlock
    0.35
    Бахар
    0.35
     ,
    
    0.35
    evos
    0.35
    ")){
    
    0.35
    ddots
    0.34
    Activations Density 0.843%

    No Known Activations