© 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. 21-GEMMASCOPE-RES-16K
    6. 13574
    Prev
    Next
    INDEX
    Explanations

    elements related to database queries and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.82
    adaptiveStyles
    -0.79
     queſta
    -0.75
    GTCX
    -0.73
    KommentareTeilen
    -0.72
     autorytatywna
    -0.71
    */),
    -0.71
    +#+#
    -0.71
     InputDecoration
    -0.71
    ConstraintMaker
    -0.70
    POSITIVE LOGITS
      
    0.36
     only
    0.32
     Snow
    0.32
                
    0.31
     Schnee
    0.30
     https
    0.28
     hopefully
    0.28
            
    0.28
    ↵
    0.27
     \\
    0.27
    Activations Density 0.323%

    No Known Activations