© 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. 5-GEMMASCOPE-RES-16K
    11. 5191
    Prev
    Next
    INDEX
    Explanations

    entities related to companies and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     back
    -0.56
    __);
    -0.49
    AddHtmlAttribute
    -0.48
    rogène
    -0.47
    ellant
    -0.46
     in
    -0.46
    ↵
    -0.46
     almost
    -0.45
     ...
    -0.44
     fast
    -0.43
    POSITIVE LOGITS
    IContainer
    0.89
    帖最后由
    0.87
    存于互联网档案馆
    0.84
     kasarigan
    0.77
    Lähteet
    0.75
    ⓧ
    0.71
    styleType
    0.71
     ComVisible
    0.70
    Przypisy
    0.70
    
    0.70
    Activations Density 0.667%

    No Known Activations