© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14572
    Prev
    Next
    INDEX
    Explanations

    keywords related to file operations and management

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

    Tokens after "Art" related to art market/industry

    np_acts-logits-general · gemini-2.0-flash

    art market

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ratulations
    -1.02
    prehensive
    -0.99
    intelligible
    -0.88
    ecutive
    -0.87
    utterstock
    -0.84
    æus
    -0.83
    polation
    -0.82
    ercises
    -0.82
    gnition
    -0.81
    andafter
    -0.80
    POSITIVE LOGITS
     pleaſure
    1.01
     ſche
    1.00
    ſelf
    0.89
     houſe
    0.87
     ſever
    0.86
     purpoſe
    0.85
     raiſ
    0.85
     köln
    0.83
     Reſ
    0.83
     Diſ
    0.83
    Activations Density 0.921%

    No Known Activations