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. 2-GEMMASCOPE-RES-16K
    6. 3829
    Prev
    Next
    INDEX
    Explanations

    quantifiers and numbers related to singular forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.91
    archiviato
    -0.63
    PageContext
    -0.61
     propOrder
    -0.61
    лтемелер
    -0.60
    ibatis
    -0.59
    ‍♀
    -0.58
    GroupLayout
    -0.58
     Numerade
    -0.57
    ATIVA
    -0.57
    POSITIVE LOGITS
    one
    2.58
    ONE
    2.26
    ones
    1.74
    ONES
    1.25
    One
    1.18
    oned
    1.07
    lone
    1.04
    Ones
    1.02
     ONE
    0.94
    rone
    0.94
    Activations Density 0.122%

    No Known Activations