© 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. 3823
    Prev
    Next
    INDEX
    Explanations

    questions or concerns expressed in a conversational context

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

    Frequently used punctuation (, . : ;)

    np_acts-logits-general · gemini-2.0-flash

    Q/A formats

    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
     ~$
    -0.93
     ~
    -0.83
    🏻‍♀️
    -0.82
     significantly
    -0.82
     ‘
    -0.81
     ostensibly
    -0.81
     (~
    -0.80
    (!)
    -0.77
     IIRC
    -0.77
     essentially
    -0.76
    POSITIVE LOGITS
    <bos>
    0.69
     AssemblyCulture
    0.65
     sortes
    0.57
     iam
    0.49
    MessageOf
    0.49
    long
    0.48
     ?
    0.48
    IMPORTED
    0.47
    vece
    0.47
     avulla
    0.47
    Activations Density 0.105%

    No Known Activations