© 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. 1-GEMMASCOPE-RES-16K
    6. 9403
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "mann," indicating a focus on specific references or topics surrounding the concept of "mann."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.56
    {}/
    -0.48
     doInBackground
    -0.47
    Voltaje
    -0.41
     prí
    -0.39
     arbejds
    -0.38
    Caratter
    -0.38
     rubrique
    -0.38
     stř
    -0.37
    roffene
    -0.37
    POSITIVE LOGITS
    ="{{
    0.62
     itſelf
    0.62
     Dental
    0.58
    physiological
    0.57
    ="<?=
    0.56
     Reſ
    0.55
    sizeof
    0.55
    <<
    0.54
    physiology
    0.54
     trick
    0.54
    Activations Density 0.187%

    No Known Activations