© 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. 25-GEMMASCOPE-RES-16K
    11. 15199
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between multiple studies or data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Italijanski
    -0.57
    AndEndTag
    -0.57
     surla
    -0.54
    styleType
    -0.49
    EndGlobalSection
    -0.49
    setVerticalGroup
    -0.48
     TabLayout
    -0.48
    Cubit
    -0.48
     resourceCulture
    -0.47
    afone
    -0.46
    POSITIVE LOGITS
     établissements
    0.48
     setempat
    0.40
    ForRow
    0.40
     unui
    0.38
     determinado
    0.37
     neighbors
    0.36
     initComponents
    0.36
     laaj
    0.36
     determinada
    0.36
     suatu
    0.35
    Activations Density 1.006%

    No Known Activations