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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11688
    Prev
    Next
    INDEX
    Explanations

    uncertainty and unpredictability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.54
    OGND
    -0.53
    Билгалдахарш
    -0.50
    fling
    -0.50
    ⟬
    -0.49
     Audiodateien
    -0.49
    webElementXpaths
    -0.49
    profen
    -0.49
     Balm
    -0.49
    nloa
    -0.48
    POSITIVE LOGITS
     unpredictable
    1.10
     unpredic
    1.05
     random
    0.89
     randomly
    0.87
     uncertain
    0.84
     uncertainty
    0.82
     randomness
    0.82
     RANDOM
    0.72
    random
    0.70
     uncertainties
    0.70
    Activations Density 0.731%

    No Known Activations