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. 8875
    Prev
    Next
    INDEX
    Explanations

    references to statistical or numerical data

    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
     Peshawar
    -0.72
     Sichuan
    -0.67
     papy
    -0.66
     Theſe
    -0.65
    writeFieldEnd
    -0.61
     laiko
    -0.60
     Wuhan
    -0.60
     mex
    -0.60
     vandens
    -0.59
     Deccan
    -0.59
    POSITIVE LOGITS
     Lithuanian
    0.85
     Lithuania
    0.82
    Lithuania
    0.82
     Latvia
    0.81
     Vilnius
    0.81
     Riga
    0.77
     Ause
    0.75
    Lithuan
    0.74
     Latvian
    0.73
    Vil
    0.72
    Activations Density 0.104%

    No Known Activations