© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10245
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to processes and operations

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

    delays or needing time

    np_acts-logits-general · gemini-2.0-flash

    time and delays

    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
     itſelf
    -0.49
     increí
    -0.49
     chofe
    -0.48
     $_"
    -0.48
     ejer
    -0.44
    pecabe
    -0.44
     occaf
    -0.44
     estadounid
    -0.44
    leſs
    -0.44
    جغرافيا
    -0.43
    POSITIVE LOGITS
     slow
    0.65
     delay
    0.65
     slowest
    0.64
     delayed
    0.63
     delaying
    0.62
     delays
    0.59
     slower
    0.56
    slow
    0.55
    Delay
    0.53
     SLOW
    0.53
    Activations Density 0.349%

    No Known Activations