© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 4886
    Prev
    Next
    INDEX
    Explanations

    anatomical and medical terms related to the body and injury

    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
    ьаж
    -0.89
    GOTREF
    -0.78
     الحره
    -0.75
    principalTable
    -0.74
    AddHtmlAttribute
    -0.72
    InputBorder
    -0.70
    setVerticalGroup
    -0.68
     Ause
    -0.66
    '},
    
    -0.64
    ɵɵelementStart
    -0.64
    POSITIVE LOGITS
    深处
    0.49
     viewDidLoad
    0.43
    ätzlich
    0.42
    aryen
    0.39
     считать
    0.39
     caused
    0.38
     calculators
    0.38
    venidos
    0.38
     Rasen
    0.37
     woning
    0.36
    Activations Density 0.547%

    No Known Activations