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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7854
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental sampling and data collection processes

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

    Ecological surveying or sampling

    np_acts-logits-general · gemini-2.0-flash

    sampling counts and locations

    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
     CreateTagHelper
    -0.68
    aarrggbb
    -0.68
     autorytatywna
    -0.67
     للمعارف
    -0.67
    TagMode
    -0.67
     engraçadas
    -0.63
     StatelessWidget
    -0.63
     MaterialApp
    -0.62
     الرياضيه
    -0.59
     mẽ
    -0.58
    POSITIVE LOGITS
     sampling
    1.18
     survey
    1.13
     surveys
    1.01
     transect
    0.96
     Sampling
    0.95
     surveyed
    0.94
    Sampling
    0.90
    survey
    0.88
     sampled
    0.88
    sampling
    0.87
    Activations Density 0.583%

    No Known Activations