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. 18-GEMMASCOPE-RES-16K
    6. 8540
    Prev
    Next
    INDEX
    Explanations

    references to healthcare and medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, math, or technical symbols

    np_acts-logits-general · gemini-2.0-flash

    exciting thing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ().__
    -0.54
     mo
    -0.52
     ha
    -0.52
     Max
    -0.52
     Min
    -0.50
     bio
    -0.48
     min
    -0.48
     mi
    -0.47
     er
    -0.47
    th
    -0.46
    POSITIVE LOGITS
     myſelf
    1.03
     Majefty
    0.99
     themſelves
    0.99
     itſelf
    0.98
     Monfieur
    0.94
     ainfi
    0.90
     himſelf
    0.89
     Jefus
    0.89
     uſe
    0.88
     Efq
    0.88
    Activations Density 0.469%

    No Known Activations