© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14432
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "have" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    csolódó
    -0.72
    évaluateur
    -0.65
    ^(@)
    -0.61
    resse
    -0.60
    يكب
    -0.58
    ).__
    -0.57
    */;
    -0.56
    ContentLoaded
    -0.56
    -------
    -0.56
    ^(@
    -0.56
    POSITIVE LOGITS
     definitely
    0.93
     really
    0.80
     certainly
    0.77
     always
    0.73
     never
    0.69
     absolutely
    0.67
     pretty
    0.66
     hardly
    0.65
    definitely
    0.62
     lots
    0.62
    Activations Density 0.185%

    No Known Activations