© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9017
    Prev
    Next
    INDEX
    Explanations

    words associated with convenience and ease of access

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

    Convenience and convenient options

    np_acts-logits-general · gemini-2.0-flash

    convenient convenience

    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
     Gallimard
    -0.49
     ExecuteAsync
    -0.45
     Letras
    -0.44
     Hø
    -0.43
    gamesh
    -0.43
    setHorizontal
    -0.42
     profondément
    -0.42
    owulf
    -0.42
    antula
    -0.40
    umask
    -0.40
    POSITIVE LOGITS
    convenience
    1.05
    convenient
    0.98
     convenience
    0.98
     convenient
    0.95
     Convenience
    0.95
     Convenient
    0.94
    Convenient
    0.93
    Convenience
    0.88
     conveniences
    0.80
     inconvenience
    0.78
    Activations Density 0.333%

    No Known Activations