© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 16103
    Prev
    Next
    INDEX
    Explanations

    quantitative data, especially measurements and statistics related to age, time, and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numerical measurements and quantities with their units (degrees, percentages, milliliters, micrograms, etc.).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.68
    tvguidetime
    -0.67
     defaultstate
    -0.60
     snippetHide
    -0.57
    WithIOException
    -0.54
    hyrchwyd
    -0.52
     виправивши
    -0.52
     RoutedEventArgs
    -0.50
     שוליים
    -0.50
    AutoModerator
    -0.49
    POSITIVE LOGITS
    bibfield
    0.59
    bibinfo
    0.48
    HomeAsUp
    0.45
    WindowListener
    0.44
     '\\;'
    0.44
     protoimpl
    0.43
    BibitemShut
    0.43
    ftagPool
    0.42
    noopener
    0.41
     CreateTagHelper
    0.41
    Activations Density 0.655%

    No Known Activations