© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10161
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements

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

    Citations, especially with years ending in "a"

    np_acts-logits-general · gemini-2.0-flash

    string manipulation after output

    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
     real
    -0.36
     $\
    -0.35
     $
    -0.35
     ersetzt
    -0.34
     Cor
    -0.34
    der
    -0.33
    <h1>
    -0.33
     of
    -0.32
     the
    -0.32
     lø
    -0.32
    POSITIVE LOGITS
    httphttps
    0.77
    rungsseite
    0.75
     autorytatywna
    0.74
     Taktlose
    0.72
     Administrativna
    0.72
    adaptiveStyles
    0.71
     للاسماء
    0.69
    IUrlHelper
    0.69
    findpost
    0.68
     EconPapers
    0.68
    Activations Density 1.355%

    No Known Activations