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. 11-GEMMASCOPE-RES-16K
    6. 6081
    Prev
    Next
    INDEX
    Explanations

    structured data or code elements related to programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obald
    -0.50
    はじめに
    -0.50
    mybatisplus
    -0.50
    esModule
    -0.50
    ReusableCell
    -0.49
    leurs
    -0.46
    abung
    -0.46
    ClassNotFound
    -0.46
    manha
    -0.46
    sequelize
    -0.45
    POSITIVE LOGITS
     autorytatywna
    0.78
    plus
    0.60
    Plus
    0.55
    tagHelperRunner
    0.54
    Gön
    0.50
    PLUS
    0.50
    Autoritní
    0.49
     impeach
    0.49
     Infinite
    0.49
    saraba
    0.49
    Activations Density 0.582%

    No Known Activations