© 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. 10-GEMMASCOPE-RES-16K
    11. 8782
    Prev
    Next
    INDEX
    Explanations

    expressions that convey intent or desire followed by the infinitive form of verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     daudz
    -0.83
    vats
    -0.62
    baix
    -0.62
    FORMAN
    -0.61
     Alen
    -0.58
    splitlines
    -0.58
    fiés
    -0.57
    martre
    -0.57
     cobra
    -0.56
     Dat
    -0.56
    POSITIVE LOGITS
     estimés
    1.01
     wanna
    0.88
    wanna
    0.85
    Wanna
    0.84
     Wanna
    0.83
     querem
    0.82
     WIC
    0.81
     entend
    0.79
     quiero
    0.76
     Gonna
    0.75
    Activations Density 0.106%

    No Known Activations