© 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. 7-GEMMASCOPE-RES-16K
    11. 15462
    Prev
    Next
    INDEX
    Explanations

    technical terms and attributes related to programming and software components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CardNumber
    -0.38
    addRow
    -0.37
     sat
    -0.35
     dis
    -0.34
    OffsetX
    -0.34
     [
    -0.33
     argparse
    -0.33
    stringValue
    -0.33
     disco
    -0.33
     record
    -0.32
    POSITIVE LOGITS
    uxxxx
    3.36
     autorytatywna
    2.55
     ویکی‌پدی
    2.22
    OGND
    2.11
    rungsseite
    2.08
     betweenstory
    2.08
    MigrationBuilder
    2.06
     Administrativna
    2.05
    expandindo
    2.05
    AndEndTag
    2.05
    Activations Density 0.246%

    No Known Activations