© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 1819
    Prev
    Next
    INDEX
    Explanations

    phrases associated with mathematical and scientific variables or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.44
     information
    -0.40
    information
    -0.38
     ascol
    -0.38
    шев
    -0.38
    ÁT
    -0.38
    teri
    -0.37
    ComponentModel
    -0.37
     Information
    -0.37
    Jerusalem
    -0.36
    POSITIVE LOGITS
    SourceChecksum
    1.14
    hyrchwyd
    0.99
    EndContext
    0.97
     يتيمه
    0.97
     оригіналу
    0.96
    BeginContext
    0.91
     estekak
    0.90
     EconPapers
    0.90
    sizeCache
    0.88
    InSection
    0.88
    Activations Density 1.204%

    No Known Activations