Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10099
    Prev
    Next
    INDEX
    Explanations

    phrases that express obligations or requirements involving the word "to"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxDecoration
    -0.58
    adpleegd
    -0.54
     грн
    -0.51
    Oh
    -0.50
     käyttää
    -0.48
     Pantal
    -0.48
     hvit
    -0.45
     Wikimédia
    -0.45
    ArgsConstructor
    -0.45
    ্ষ
    -0.44
    POSITIVE LOGITS
    anskje
    0.73
     offer
    0.68
    menuStrip
    0.68
     worry
    0.67
     spare
    0.63
     AssemblyCompany
    0.62
     contend
    0.61
     OFFER
    0.58
    QMetaType
    0.58
    IntoConstraints
    0.57
    Activations Density 0.105%

    No Known Activations