© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 89629
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -1.03
    expandindo
    -0.86
    MLLoader
    -0.82
    SizeF
    -0.81
    Спољашње
    -0.75
    parsedMessage
    -0.69
    يكب
    -0.64
    MethodManager
    -0.63
    DockStyle
    -0.62
    BufferException
    -0.62
    POSITIVE LOGITS
     везе
    3.98
     veze
    2.61
     ostavi
    1.30
     poveznice
    0.79
     povezave
    0.60
     vez
    0.58
    vezet
    0.51
     روابط
    0.49
     linkovi
    0.47
     vezet
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.