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. 14-GEMMASCOPE-RES-16K
    6. 10925
    Prev
    Next
    INDEX
    Explanations

    conditional phrases indicating caution or considerations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.50
    ்கு
    -0.48
     padi
    -0.45
    neurial
    -0.44
     thơm
    -0.43
     geändert
    -0.42
     montré
    -0.41
    nutie
    -0.41
     NgModule
    -0.41
    prisma
    -0.41
    POSITIVE LOGITS
    RenderAtEndOf
    0.83
    tvguidetime
    0.72
    setupUi
    0.67
     dealing
    0.63
    antMatchers
    0.63
    TintMode
    0.63
    figsize
    0.62
    indexPath
    0.62
    RegressionTest
    0.62
     AssemblyTitle
    0.61
    Activations Density 0.378%

    No Known Activations