© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10650
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters associated with string declarations

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

    Opening characters of code/strings

    np_acts-logits-general · gemini-2.0-flash

    description of freshness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.93
     виправивши
    -0.81
    %"),
    -0.80
    帖最后由
    -0.78
    UnusedPrivate
    -0.76
    <unused8>
    -0.75
     laſſen
    -0.75
    [@BOS@]
    -0.75
    Hentet
    -0.75
    <unused14>
    -0.74
    POSITIVE LOGITS
    $('
    0.35
     |
    0.31
    ("
    0.29
     -
    0.29
     :
    0.28
     schwar
    0.28
    ','
    0.27
    mathcal
    0.27
     own
    0.27
     Geschlecht
    0.26
    Activations Density 0.336%

    No Known Activations