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. 5-GEMMASCOPE-RES-16K
    6. 2108
    Prev
    Next
    INDEX
    Explanations

    terms related to postoperative evaluations and processes

    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
    -1.05
     propertyName
    -0.96
     Мексичка
    -0.94
    LAUGHTER
    -0.91
    Kjelder
    -0.87
    ://"
    -0.87
     متعلقه
    -0.86
     XCTest
    -0.85
    Kuri
    -0.85
    rrggbb
    -0.85
    POSITIVE LOGITS
     Post
    2.64
     post
    2.63
    post
    2.60
    Post
    2.56
     POST
    2.34
     posts
    2.21
     Posts
    2.16
    POST
    2.09
    Posts
    1.96
    posts
    1.94
    Activations Density 0.056%

    No Known Activations