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. 8730
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, possibly in academic or scientific contexts

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

    Tokens starting with "Wo" or "wo"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Wo

    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
    RectangleBorder
    -0.66
     فريبيس
    -0.65
    Попис
    -0.64
    ities
    -0.61
     itſelf
    -0.60
     uintptr
    -0.59
    tabular
    -0.59
    hematical
    -0.56
     <>",
    -0.56
    Spoljašnje
    -0.55
    POSITIVE LOGITS
     Wo
    0.79
    Wo
    0.73
     Wohl
    0.70
     Woj
    0.70
    vo
    0.69
     vo
    0.69
     Wor
    0.67
     Woll
    0.67
     Wolves
    0.67
    voz
    0.67
    Activations Density 0.098%

    No Known Activations