© 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. 14932
    Prev
    Next
    INDEX
    Explanations

    instances of the word "reply" and its variations in a technical or programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    UrlResolution
    -0.54
    Gardner
    -0.43
    <h2>
    -0.42
    Einstein
    -0.40
     chrétien
    -0.40
     Ministério
    -0.38
     inoxydable
    -0.38
    ən
    -0.38
     ContentValues
    -0.38
    .")
    
    -0.38
    POSITIVE LOGITS
     Reply
    0.82
    Reply
    0.74
     reply
    0.74
     Dialog
    0.72
     REPLY
    0.71
    reply
    0.70
     affili
    0.69
     dlg
    0.69
     dialog
    0.68
    REPLY
    0.66
    Activations Density 0.128%

    No Known Activations