© 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 EvalsExportsinterp-engineNEWAPI 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. 8657
    Prev
    Next
    INDEX
    Explanations

    author information and licensing details in documents

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

    Code, copyright, or license information

    np_acts-logits-general · gemini-2.0-flash

    copyright notices and dates

    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
     Pilihan
    -0.41
     montañas
    -0.40
     Domínguez
    -0.39
     Sloveniji
    -0.39
     Lengkap
    -0.38
     Gubernur
    -0.38
     ovan
    -0.38
     Biôgrafia
    -0.38
    <b>
    -0.37
     araña
    -0.37
    POSITIVE LOGITS
    httphttps
    0.69
    +#+
    0.63
    الإنجليزية
    0.61
    tagHelperRunner
    0.60
    出版年
    0.58
    LookAnd
    0.57
    RTCK
    0.57
     Coding
    0.57
    ViewImports
    0.50
     betweenstory
    0.50
    Activations Density 0.387%

    No Known Activations