© 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. 34-GEMMASCOPE-RES-16K
    11. 11518
    Prev
    Next
    INDEX
    Explanations

    code snippets or components associated with programming and data structures

    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
    الدراسه
    -0.48
    PMailer
    -0.46
    sendRedirect
    -0.44
    CGRectMake
    -0.42
    jspx
    -0.41
    DataOutputStream
    -0.41
    orianCalendar
    -0.41
     ←
    -0.39
    :^(
    -0.39
    bufio
    -0.38
    POSITIVE LOGITS
     Object
    1.05
     object
    1.04
    Object
    0.94
     Objekt
    0.81
     objects
    0.81
    object
    0.77
     OBJECT
    0.77
     Objects
    0.71
    OBJECT
    0.70
     oggetto
    0.68
    Activations Density 0.323%

    No Known Activations