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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 7342
    Prev
    Next
    INDEX
    Explanations

    references to Disney and its related media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "fairy" and related fairytale words

    np_acts-logits-general · gemini-2.0-flash

    fairy tales

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.60
     Sumner
    -0.59
     IBA
    -0.59
     utafitiHapana
    -0.55
     MainAxisSize
    -0.55
    picasso
    -0.50
     Gila
    -0.50
    ènements
    -0.50
    illots
    -0.49
     مخطط
    -0.48
    POSITIVE LOGITS
     fairy
    1.24
     Disney
    1.21
     Cinderella
    1.12
     Fairy
    1.12
     fairytale
    1.10
    Disney
    1.09
     princess
    1.07
     prince
    1.06
    Cinderella
    1.06
     princes
    1.04
    Activations Density 0.134%

    No Known Activations