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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 9635
    Prev
    Next
    INDEX
    Explanations

    phrases related to job roles and responsibilities within organizations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.83
     ModelExpression
    -0.75
    fromnode
    -0.71
     réglable
    -0.69
     resourceCulture
    -0.69
    IntoConstraints
    -0.68
     cardiaque
    -0.66
    routeProvider
    -0.65
     métallique
    -0.64
     endblock
    -0.64
    POSITIVE LOGITS
     Microsoft
    0.82
     IBM
    0.75
     Sony
    0.73
     Google
    0.66
     Philips
    0.65
     Samsung
    0.64
     Siemens
    0.64
     Phillips
    0.64
     Coca
    0.63
    Microsoft
    0.61
    Activations Density 1.541%

    No Known Activations