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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9626
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize effort and improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    SharedCtor
    -0.51
    Spoljašnje
    -0.50
     Fewer
    -0.46
    //});
    -0.46
     кӀ
    -0.46
    AutoScaleMode
    -0.45
    anskrit
    -0.45
    greater
    -0.45
     bigger
    -0.45
     насеље
    -0.45
    POSITIVE LOGITS
     much
    1.41
    much
    1.24
    Much
    1.21
     mucho
    1.17
     Much
    1.16
     MUCH
    1.12
     considerably
    1.05
     beaucoup
    1.02
     muchísimo
    0.94
    slightly
    0.90
    Activations Density 0.172%

    No Known Activations