© 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. 0-GEMMASCOPE-RES-16K
    11. 8332
    Prev
    Next
    INDEX
    Explanations

    instances of specific phonetic patterns or morphemes in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sûre
    -0.52
     brancas
    -0.52
     SIAM
    -0.51
     Minna
    -0.51
     DMS
    -0.51
     ActionResult
    -0.50
     sûrement
    -0.49
    OrBuilder
    -0.48
     Nowadays
    -0.48
    Nowadays
    -0.48
    POSITIVE LOGITS
    новниш
    0.85
     Lou
    0.79
    esModule
    0.78
     Ron
    0.73
    BeginInit
    0.69
    osa
    0.69
    ьаж
    0.68
    CPtr
    0.66
    исленность
    0.66
     suppress
    0.66
    Activations Density 0.060%

    No Known Activations