© 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. 40-GEMMASCOPE-RES-16K
    6. 2688
    Prev
    Next
    INDEX
    Explanations

    occurrences of the ampersand symbol and its associated context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     among
    -0.64
    ,
    -0.56
     nevertheless
    -0.51
     amongst
    -0.49
     AMONG
    -0.48
    among
    -0.47
     Among
    -0.45
     in
    -0.45
    Among
    -0.44
     however
    -0.43
    POSITIVE LOGITS
    amp
    1.19
     Associates
    0.94
     friends
    0.94
     compañía
    0.88
     Company
    0.87
     company
    0.85
    friends
    0.85
     Friends
    0.85
     companhia
    0.84
    ndash
    0.83
    Activations Density 0.493%

    No Known Activations