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. 12-GEMMASCOPE-RES-16K
    6. 636
    Prev
    Next
    INDEX
    Explanations

    terms related to hobbies and interests, particularly those involving sewing, crafting, and amateur activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GenerationType
    -0.67
     AspNetCore
    -0.62
    RegressionTest
    -0.60
    Filmografie
    -0.59
     choreographer
    -0.58
     kasarigan
    -0.58
     للاسماء
    -0.58
    IsContent
    -0.57
    urlpatterns
    -0.56
    Chore
    -0.56
    POSITIVE LOGITS
     hobby
    1.20
     Hobby
    0.89
    hobby
    0.84
    Hobby
    0.77
     enthusiasts
    0.75
     hobbies
    0.73
     enthusiast
    0.72
     للمعارف
    0.67
    Amateur
    0.65
     amateur
    0.64
    Activations Density 0.323%

    No Known Activations