© 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. 9-GEMMASCOPE-RES-16K
    11. 1194
    Prev
    Next
    INDEX
    Explanations

    terms related to medical or scientific classifications and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     encephalitis
    -0.85
     Ambiental
    -0.79
    сылкі
    -0.79
     Nuo
    -0.77
     Normdatei
    -0.74
    Urb
    -0.74
     mourut
    -0.73
     Orrell
    -0.73
     délib
    -0.73
    раздо
    -0.72
    POSITIVE LOGITS
     recyclerView
    0.85
     Scherer
    0.84
     Collar
    0.76
     union
    0.75
     Muk
    0.74
     Kirsch
    0.73
     Anderson
    0.73
    팎
    0.73
     Yel
    0.73
     Zel
    0.72
    Activations Density 1.426%

    No Known Activations