© 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. 11-GEMMASCOPE-RES-16K
    11. 6433
    Prev
    Next
    INDEX
    Explanations

    sequences of repeated characters or specific structural elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Oates
    -0.65
     Lovato
    -0.58
    Kand
    -0.58
    ņš
    -0.58
    تل
    -0.57
    ل
    -0.57
     Gunn
    -0.56
     nit
    -0.56
    vania
    -0.55
     Sil
    -0.55
    POSITIVE LOGITS
     nakalista
    0.98
    EndContext
    0.93
     <<<<<<<<<<<<<<
    0.92
     Spaniard
    0.87
     Orrell
    0.85
    انيف
    0.83
     &___
    0.81
     useAppContext
    0.81
     SPIE
    0.80
     Dostupné
    0.79
    Activations Density 0.183%

    No Known Activations