© 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 - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 8711
    Prev
    Next
    INDEX
    Explanations

    expressions of humor, particularly in relation to laughter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PyExc
    -0.79
    ⟬
    -0.78
     itſelf
    -0.78
    存于互联网档案馆
    -0.77
    ſelf
    -0.76
     snippetHide
    -0.76
    NameInMap
    -0.75
     myſelf
    -0.71
     vectorielle
    -0.68
     increí
    -0.66
    POSITIVE LOGITS
     Lol
    0.95
     lol
    0.94
    Lol
    0.88
    lol
    0.85
     LOL
    0.80
    LOL
    0.76
     haha
    0.72
     Haha
    0.66
     Ha
    0.64
     lmao
    0.64
    Activations Density 0.273%

    No Known Activations