© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 15678
    Prev
    Next
    INDEX
    Explanations

    phrases related to database operations, particularly those involving user roles and branches

    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>
    -0.86
    rungsseite
    -0.75
    Hentet
    -0.71
    ViewImports
    -0.70
    contentLoaded
    -0.69
    WriteTagHelper
    -0.68
     AssemblyProduct
    -0.65
     AssemblyTitle
    -0.62
    WithIOException
    -0.58
    RenderAtEndOf
    -0.58
    POSITIVE LOGITS
     Mahabhar
    0.64
     ARA
    0.59
     synag
    0.59
     AspNetCore
    0.58
    ranath
    0.56
    rature
    0.56
     Athenians
    0.55
    endphp
    0.54
    tagHelperRunner
    0.54
     RSC
    0.54
    Activations Density 0.460%

    No Known Activations