© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105773
    Prev
    Next
    INDEX
    Explanations

    content related to literature and popular culture, particularly in a humorous or critical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     oreilles
    -0.34
     חיצוניים
    -0.33
    TIMORE
    -0.32
     קו
    -0.32
     Türen
    -0.32
     Händen
    -0.31
     mercies
    -0.31
    ࿐
    -0.31
     inclu
    -0.31
     incluyen
    -0.31
    POSITIVE LOGITS
     ſta
    0.57
    хьтан
    0.55
    Vidite
    0.50
     étoit
    0.49
    IVEREF
    0.47
    ̈́
    0.47
     autorytatywna
    0.46
    contentLoaded
    0.46
     AppCompatTheme
    0.44
    Spoljašnje
    0.44
    Activations Density 0.036%

    No Known Activations