Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 11037
    Prev
    Next
    INDEX
    Explanations

    references to swimming pools

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

    Code or text mentioning "Pool"

    np_acts-logits-general · gemini-2.0-flash

    pool of, pool project, pooled ratios

    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
    IUrlHelper
    -0.64
    Ĝ
    -0.59
    DIRS
    -0.55
     tolua
    -0.51
    Nem
    -0.51
    bootstrapcdn
    -0.51
    >>>
    -0.49
    eph
    -0.49
    cientific
    -0.49
    recrow
    -0.48
    POSITIVE LOGITS
    side
    0.78
    pools
    0.73
    IsContent
    0.70
     pools
    0.70
    EndContext
    0.69
    mybatisplus
    0.69
    SIDE
    0.67
     فريبيس
    0.62
    othek
    0.61
    Pools
    0.61
    Activations Density 0.074%

    No Known Activations