© 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-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7362
    Prev
    Next
    INDEX
    Explanations

    the word "hu" and variations of it, indicating a focus on expressions of laugh or amusement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 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
    __*/
    -0.66
    ftagPool
    -0.61
     doInBackground
    -0.52
    HtmlAttribute
    -0.52
    +:+
    -0.51
    etyl
    -0.51
    }}},
    -0.51
    ardia
    -0.50
    _^
    -0.50
    CardBody
    -0.50
    POSITIVE LOGITS
     gem
    0.88
     gems
    0.87
     Gems
    0.80
    Gem
    0.78
    Gems
    0.77
    gem
    0.76
     Gem
    0.75
    gems
    0.72
     treasures
    0.72
     autorytatywna
    0.67
    Activations Density 0.061%

    No Known Activations