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. 10034
    Prev
    Next
    INDEX
    Explanations

    future-oriented statements and intentions related to research and development

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

    Following "to," "will," "by," or "have."

    np_acts-logits-general · gemini-2.0-flash

    research activities and findings

    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
     domestiques
    -0.74
     pauv
    -0.73
     alimentaires
    -0.71
     mijne
    -0.71
     copertura
    -0.68
     scolaires
    -0.68
     spirituale
    -0.67
     sobra
    -0.64
     storica
    -0.64
     heals
    -0.64
    POSITIVE LOGITS
    ----</
    0.64
     offer
    0.63
    archiviato
    0.62
    */),
    0.60
     provide
    0.58
    曖昧さ回避
    0.58
     re
    0.57
     set
    0.55
    💇
    0.55
     regularly
    0.53
    Activations Density 0.862%

    No Known Activations