© 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. 11520
    Prev
    Next
    INDEX
    Explanations

    references to clickable links and additional data or resources

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

    "For" followed by "additional"

    np_acts-logits-general · gemini-2.0-flash

    full or additional content

    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
    EClass
    -0.50
    ⓧ
    -0.48
     disambiguazione
    -0.48
     GenerationType
    -0.48
    Rüyada
    -0.41
    retudo
    -0.41
     跳转至
    -0.39
    DataAnnotations
    -0.39
    allowNull
    -0.39
    rån
    -0.38
    POSITIVE LOGITS
     full
    1.17
     complete
    1.00
     volledige
    0.94
     FULL
    0.92
    complete
    0.90
    完整
    0.90
    full
    0.89
     vollständ
    0.88
    完整的
    0.88
     Full
    0.84
    Activations Density 0.587%

    No Known Activations