© 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. 13-GEMMASCOPE-RES-16K
    6. 8970
    Prev
    Next
    INDEX
    Explanations

    specific terms related to various types and properties of substances or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.58
     صوتيه
    -0.57
     estekak
    -0.57
     propOrder
    -0.57
    __(/*!
    -0.52
     createState
    -0.47
     jScrollPane
    -0.44
     فريبيس
    -0.44
     initComponents
    -0.44
    SourceChecksum
    -0.43
    POSITIVE LOGITS
    endtime
    0.54
     betweenstory
    0.50
     nothwendig
    0.49
     dintre
    0.48
    filepath
    0.48
    tonode
    0.47
     fiecare
    0.47
    rašymas
    0.43
     testSet
    0.43
     unſ
    0.42
    Activations Density 1.877%

    No Known Activations