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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 7734
    Prev
    Next
    INDEX
    Explanations

    scientific terms and concepts related to biological processes and scientific methodologies

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

    preceding "must," "requires," or forms of "to be."

    np_acts-logits-general · gemini-2.0-flash

    requires something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    BASELINE
    -0.52
     shame
    -0.46
    extAlignment
    -0.45
     Comparator
    -0.43
    Decoded
    -0.42
     Shame
    -0.42
     anom
    -0.42
    shame
    -0.41
     gemeint
    -0.40
    az
    -0.40
    POSITIVE LOGITS
     requires
    2.79
     require
    2.62
     Requires
    2.40
    requires
    2.34
     requiring
    2.25
    require
    2.20
    Requires
    2.15
     Require
    2.13
     requiere
    2.03
     REQU
    1.90
    Activations Density 1.001%

    No Known Activations