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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 10720
    Prev
    Next
    INDEX
    Explanations

    expressions and references related to passion and enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.96
    bootstrapcdn
    -0.86
     Herrick
    -0.75
    Rüyada
    -0.73
    adə
    -0.66
     Mère
    -0.65
    orological
    -0.64
     ModelRenderer
    -0.63
     Majesté
    -0.63
     Gaulle
    -0.63
    POSITIVE LOGITS
     passion
    2.18
     Passion
    2.09
    Passion
    2.01
    passion
    2.01
     passions
    1.80
     passionate
    1.70
    assioned
    1.59
     passione
    1.56
     pasión
    1.51
     passionately
    1.47
    Activations Density 0.062%

    No Known Activations