© 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. 34-GEMMASCOPE-RES-16K
    11. 7557
    Prev
    Next
    INDEX
    Explanations

    HTML tags and elements related to structured data representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -1.03
     Administrativna
    -0.88
    síða
    -0.83
     jsPsych
    -0.81
     تضيفلها
    -0.79
     BrowserModule
    -0.79
     ©️
    -0.79
    ConstraintMaker
    -0.78
    setVerticalGroup
    -0.77
    GOTREF
    -0.77
    POSITIVE LOGITS
     nämlich
    0.24
     infatti
    0.23
    ⓧ
    0.21
    でご
    0.20
     wst
    0.20
     ért
    0.20
    <i>
    0.19
    お子
    0.19
     förs
    0.19
     подряд
    0.18
    Activations Density 0.071%

    No Known Activations