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. 9841
    Prev
    Next
    INDEX
    Explanations

    pronouns and words related to possession or relationships

    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
    Personendaten
    -0.71
    ]--;
    -0.71
    arque
    -0.69
    migrationBuilder
    -0.64
    prnewswire
    -0.64
    ⁩
    -0.62
    intele
    -0.61
    \|^{
    -0.61
    ℗
    -0.58
    formKey
    -0.58
    POSITIVE LOGITS
     pinulongan
    0.62
     Descubre
    0.52
     thermique
    0.50
     glyphicon
    0.47
     ویکی‌پدیای
    0.46
    DockStyle
    0.46
    ыгана
    0.46
    favorited
    0.46
    摘
    0.46
     oreille
    0.46
    Activations Density 0.473%

    No Known Activations