© 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. 20-GEMMASCOPE-RES-16K
    6. 10512
    Prev
    Next
    INDEX
    Explanations

    specific biochemical terminology or phrases related to genetic information and molecular biology

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

    Strings of repeated or non-alphanumeric characters

    np_acts-logits-general · gemini-2.0-flash

    scientific suffixes like caser, gaussi

    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
    n
    -0.84
    l
    -0.82
    li
    -0.75
    t
    -0.74
    r
    -0.71
    m
    -0.71
    ng
    -0.71
    ness
    -0.70
    s
    -0.69
    te
    -0.69
    POSITIVE LOGITS
    aaaaaaaa
    0.88
    aaaa
    0.85
    aaaaa
    0.84
    aaaaaa
    0.80
    aaa
    0.72
    ollectionView
    0.71
    posedge
    0.69
    ionView
    0.65
    اااا
    0.65
     étoit
    0.64
    Activations Density 1.006%

    No Known Activations