© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4376
    Prev
    Next
    INDEX
    Explanations

    references to various swimming pools and water-related activities

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

    pools, baths, or swimming

    np_acts-logits-general · gemini-2.0-flash

    pool or swim

    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
    GOTREF
    -0.59
     Catawiki
    -0.55
    richTextPanel
    -0.52
    tagHelperRunner
    -0.51
    ctrons
    -0.50
     peggio
    -0.47
     carbono
    -0.46
     propOrder
    -0.46
    lags
    -0.45
     مرئيه
    -0.44
    POSITIVE LOGITS
     swimming
    1.00
     swim
    0.91
     Swimming
    0.90
    Swimming
    0.86
    swimming
    0.84
     pool
    0.83
     Swim
    0.79
     swimmers
    0.79
     zwem
    0.79
     piscina
    0.76
    Activations Density 0.054%

    No Known Activations