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. 8569
    Prev
    Next
    INDEX
    Explanations

    terms related to official authority or documentation

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

    Following the word "official"

    np_acts-logits-general · gemini-2.0-flash

    official followed by noun

    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
     שוליים
    -0.86
    expandindo
    -0.77
    enumi
    -0.67
    esgue
    -0.66
     ItemStack
    -0.65
    writeField
    -0.65
    enumii
    -0.64
    InputTagHelper
    -0.61
    hnia
    -0.61
     surla
    -0.61
    POSITIVE LOGITS
    OFFICIAL
    1.14
     OFFICIAL
    1.05
     official
    1.05
     Official
    0.97
     unofficial
    0.91
    Official
    0.87
    official
    0.86
     officiels
    0.84
     Officially
    0.83
     offizi
    0.79
    Activations Density 0.065%

    No Known Activations