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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12477
    Prev
    Next
    INDEX
    Explanations

    references to patterns and trends in various contexts

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

    "pattern" or "patterns"

    np_acts-logits-general · gemini-2.0-flash

    identifying patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wohnzimmer
    -0.53
    ellido
    -0.43
     prawie
    -0.41
     sepenuhnya
    -0.41
     >=",
    -0.40
    InjectMocks
    -0.39
    Deine
    -0.39
     tenaga
    -0.39
     Belf
    -0.38
     Electricity
    -0.38
    POSITIVE LOGITS
     pattern
    1.24
     Pattern
    1.18
     patterns
    1.14
    pattern
    1.13
     PATTERN
    1.13
    Pattern
    1.11
     Patterns
    1.05
    PATTERN
    1.00
    Patterns
    0.96
    patterns
    0.90
    Activations Density 0.155%

    No Known Activations