Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2557
    Prev
    Next
    INDEX
    Explanations

    elements related to experimental results and comparisons

    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
     StatelessWidget
    -0.74
     المعيارى
    -0.71
    UpInside
    -0.70
     kasarigan
    -0.70
     propOrder
    -0.70
     MenuView
    -0.70
    AsUp
    -0.68
    fromnode
    -0.68
    withIdentifier
    -0.67
     autorytatywna
    -0.66
    POSITIVE LOGITS
    Results
    0.92
     results
    0.87
    結果
    0.87
     Results
    0.86
     Surprisingly
    0.85
     surprisingly
    0.83
    Surprisingly
    0.82
    results
    0.81
     結果
    0.81
    结果
    0.81
    Activations Density 0.983%

    No Known Activations