© 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. 2-GEMMASCOPE-RES-16K
    6. 1715
    Prev
    Next
    INDEX
    Explanations

    terms related to accuracy and precision

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ev
    -0.60
     ویکی‌آمباردا
    -0.55
    endregion
    -0.55
     Davies
    -0.55
     intoxic
    -0.55
    ly
    -0.54
    roek
    -0.54
     fl
    -0.54
    ress
    -0.52
    acaktır
    -0.51
    POSITIVE LOGITS
     Matching
    0.98
     matching
    0.98
     accuracy
    0.94
    Matching
    0.92
     Accurate
    0.87
    matching
    0.87
     Accuracy
    0.84
     matched
    0.82
    accuracy
    0.81
     ACCUR
    0.80
    Activations Density 0.093%

    No Known Activations