© 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. 15-GEMMASCOPE-RES-16K
    11. 3207
    Prev
    Next
    INDEX
    Explanations

    references to various types of verification or validation processes

    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
     gyerme
    -0.68
     remonter
    -0.65
     மற்ற
    -0.61
    เย็น
    -0.60
     modernos
    -0.60
     termé
    -0.59
     démission
    -0.59
     jutaan
    -0.59
    ťaž
    -0.57
    ยาว
    -0.57
    POSITIVE LOGITS
     Prze
    0.82
     Мексичка
    0.75
     xhr
    0.72
     Vý
    0.72
    Prze
    0.69
     הה
    0.69
     SDLK
    0.69
    :✨
    0.69
    bellar
    0.68
     IEnumerator
    0.68
    Activations Density 0.066%

    No Known Activations