Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 10214
    Prev
    Next
    INDEX
    Explanations

    titles and roles related to professionals in various fields, particularly within the arts and education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     상세
    -0.67
    autres
    -0.61
    SequentialGroup
    -0.54
    ьаж
    -0.52
    seamnă
    -0.51
     <>",
    -0.51
    ibase
    -0.51
    IVEREF
    -0.50
    other
    -0.47
     entanto
    -0.47
    POSITIVE LOGITS
     author
    0.87
     philanthropist
    0.86
     former
    0.79
     publisher
    0.73
     lover
    0.72
     occasional
    0.71
     bestselling
    0.71
     owner
    0.70
     fundraiser
    0.70
     host
    0.70
    Activations Density 0.165%

    No Known Activations