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. 7618
    Prev
    Next
    INDEX
    Explanations

    strong positive sentiments about characters and story elements in books.

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

    descriptive language related to a book review with a focus on characters and plot development.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    attributes or descriptions of main characters and key elements in stories or reviews.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot
    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
    •Literature
    attributes or descriptions of main characters and key elements in stories or reviews

    No Comments

    Negative Logits
    出版年
    -0.75
    AddTagHelper
    -0.72
    CompleteListener
    -0.66
     ModelExpression
    -0.64
    DockStyle
    -0.63
    djangoproject
    -0.59
    FieldNumber
    -0.58
    ponses
    -0.55
     brome
    -0.52
    ViewFeatures
    -0.52
    POSITIVE LOGITS
     characters
    1.98
     character
    1.78
    characters
    1.57
     Characters
    1.52
    character
    1.51
    Characters
    1.50
     personnages
    1.41
     CHARACTERS
    1.37
     personajes
    1.36
     Character
    1.34
    Activations Density 0.241%

    No Known Activations