© 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. 20-GEMMASCOPE-RES-16K
    6. 8483
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     [
    -0.42
    ↵↵
    -0.41
    -
    -0.40
      
    -0.40
     
    -0.38
     (
    -0.37
     and
    -0.36
     be
    -0.36
     I
    -0.34
    [
    -0.34
    POSITIVE LOGITS
    ValueStyle
    10.63
    tagHelperRunner
    2.25
    SourceChecksum
    2.03
     autorytatywna
    1.85
    AddTagHelper
    1.81
    AndEndTag
    1.79
     CreateTagHelper
    1.63
     resourceCulture
    1.60
     utafitiHapana
    1.56
     disambiguazione
    1.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.