© 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. 41-GEMMASCOPE-RES-16K
    6. 7780
    Prev
    Next
    INDEX
    Explanations

    specific numeric sequences and abbreviations related to data or references in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndPassword
    -0.43
     CURLOPT
    -0.38
     znaczy
    -0.36
     og
    -0.36
    StructEnd
    -0.35
    Fra
    -0.35
     fra
    -0.35
     considérons
    -0.34
    ogne
    -0.33
    BitConverter
    -0.33
    POSITIVE LOGITS
     och
    0.66
     <<<<<<<<<<<<<<
    0.49
     då
    0.48
     där
    0.48
     även
    0.47
     inför
    0.47
    ARROLL
    0.47
     mellan
    0.47
     innan
    0.47
     från
    0.47
    Activations Density 0.143%

    No Known Activations