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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 3913
    Prev
    Next
    INDEX
    Explanations

    data types and method signatures in programming contexts

    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
    ly
    -0.83
    ling
    -0.75
    ibli
    -0.71
     Baş
    -0.70
    cie
    -0.68
     Pais
    -0.68
    Morte
    -0.67
    er
    -0.67
    raim
    -0.66
    tangentMode
    -0.65
    POSITIVE LOGITS
    setDo
    0.84
     Nema
    0.81
     SqlCommand
    0.81
    WriteLiteral
    0.79
     femininos
    0.76
    {{$
    0.73
    PointerException
    0.73
    mendations
    0.72
    antMatchers
    0.71
    ึกษา
    0.71
    Activations Density 0.035%

    No Known Activations