© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 13583
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.63
    RegistryLite
    -0.54
    份
    -0.51
    GeneratedCode
    -0.50
    rend
    -0.50
    RenderAtEndOf
    -0.49
    ët
    -0.48
    Etymology
    -0.48
    шк
    -0.47
     cir
    -0.47
    POSITIVE LOGITS
     inoxydable
    0.73
     Efq
    0.69
     plufieurs
    0.67
     stället
    0.66
     enfans
    0.65
    raborty
    0.65
     prêtres
    0.64
    цездатний
    0.64
     ExecuteAsync
    0.62
    นะนำ
    0.62
    Activations Density 2.429%

    No Known Activations