© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 14892
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas and quotation marks

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

    Quoted alphanumeric identifiers

    np_acts-logits-general · gemini-2.0-flash

    GUIDs and code separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ‘
    -0.96
    =’
    -0.85
     entanto
    -0.83
    (‘
    -0.71
    prav
    -0.70
    Viitteet
    -0.69
     (‘
    -0.69
     obstante
    -0.64
     们
    -0.63
    .’
    -0.61
    POSITIVE LOGITS
    '".
    0.92
    '",
    0.91
    '"
    0.90
    ",
    0.89
    )".
    0.88
    ")
    0.82
    )",
    0.81
     Baillargeon
    0.81
     NSCoder
    0.80
    ']").
    0.80
    Activations Density 0.149%

    No Known Activations