© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 2366
    Prev
    Next
    INDEX
    Explanations

    code snippets or technical markup related to programming structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     становника
    -0.58
     AttributeSet
    -0.58
    цездатний
    -0.58
    msgTypes
    -0.55
    mogorov
    -0.53
     sẻ
    -0.52
    jsxFileName
    -0.52
    MethodManager
    -0.51
     referenties
    -0.51
     cref
    -0.50
    POSITIVE LOGITS
    catch
    1.21
     catch
    1.06
     Catch
    0.93
    endregion
    0.84
     CATCH
    0.83
     catching
    0.83
    CATCH
    0.82
    else
    0.81
    Catch
    0.78
     catches
    0.71
    Activations Density 0.211%

    No Known Activations