© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 11070
    Prev
    Next
    INDEX
    Explanations

    conversational phrases and informal dialogue in French

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

    French language and/or math symbols

    np_acts-logits-general · gemini-2.0-flash

    French and English technical terms

    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
    WebElementEntity
    -0.61
    ActionCreators
    -0.52
    contentLoaded
    -0.52
     CURIAM
    -0.49
    IUrlHelper
    -0.49
    TypedDataSet
    -0.48
    omitempty
    -0.48
     unknownFields
    -0.47
     怎样
    -0.47
     становника
    -0.47
    POSITIVE LOGITS
    Probl
    0.40
     régionales
    0.36
     glyphicon
    0.36
    Objective
    0.35
     ça
    0.34
     ps
    0.34
    roleum
    0.34
     Probl
    0.34
     personally
    0.34
    dian
    0.34
    Activations Density 0.271%

    No Known Activations