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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-GEMMASCOPE-RES-16K
    6. 3458
    Prev
    Next
    INDEX
    Explanations

    references to COVID-19 events and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -1.10
     ModelExpression
    -0.79
     kaarangay
    -0.76
     Administrativna
    -0.75
    Rujuakan
    -0.75
    хьтан
    -0.74
    المشاركات
    -0.73
    Personensuche
    -0.73
    ConstraintMaker
    -0.72
     betweenstory
    -0.70
    POSITIVE LOGITS
    spunk
    0.59
     magari
    0.55
    Slf
    0.54
    ylvan
    0.53
    ulario
    0.51
     chemins
    0.50
    mathrm
    0.50
    𝙫
    0.50
    skyl
    0.50
    🏼
    0.50
    Activations Density 0.026%

    No Known Activations