© 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. 27746
    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
    ValueGenerated
    -0.39
    ServletRequest
    -0.39
     charge
    -0.38
     repair
    -0.37
    luß
    -0.37
    nonatomic
    -0.36
    ajaran
    -0.36
    OrNull
    -0.35
    ///
    -0.35
     ✭✭
    -0.34
    POSITIVE LOGITS
    بوابة
    4.78
    Portail
    2.53
    Portale
    1.93
     بوابة
    1.59
    Portály
    1.33
    Datuak
    1.27
     tartalomajánló
    1.21
     незавершена
    1.12
     Portail
    1.09
     nahilalakip
    1.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.