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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3046
    Prev
    Next
    INDEX
    Explanations

    keywords related to political parties, clubs, and organizational structures

    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
     CreateTagHelper
    -0.98
    AddTagHelper
    -0.97
    styleType
    -0.97
    InputBorder
    -0.97
    findpost
    -0.95
    IBarButtonItem
    -0.89
     AssemblyProduct
    -0.89
    .*")]
    -0.84
    WriteTagHelper
    -0.83
    UnusedPrivate
    -0.82
    POSITIVE LOGITS
     company
    0.62
     town
    0.62
     corporation
    0.55
     ciutat
    0.55
     also
    0.50
     council
    0.49
     club
    0.49
     city
    0.48
     الشركة
    0.47
     firm
    0.47
    Activations Density 0.485%

    No Known Activations