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. 20-GEMMASCOPE-RES-16K
    6. 12236
    Prev
    Next
    INDEX
    Explanations

    string delimiters and punctuation marks

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

    Double quotes followed by a comma

    np_acts-logits-general · gemini-2.0-flash

    punctuation and special characters

    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
     ‘
    -0.79
     (‘
    -0.69
    DotNetBar
    -0.64
    (‘
    -0.64
    =’
    -0.64
     entanto
    -0.63
    leyebilirsiniz
    -0.58
     visione
    -0.57
     obstante
    -0.56
    sive
    -0.56
    POSITIVE LOGITS
    ",
    0.99
    '",
    0.98
    %",
    0.93
    )",
    0.92
    ?",
    0.87
    '"
    0.87
    '".
    0.86
    )".
    0.83
    $",
    0.81
     Walpole
    0.81
    Activations Density 0.087%

    No Known Activations