© 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. 2-GEMMASCOPE-RES-16K
    11. 15385
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and phrases indicating structure and functionality in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Xna
    -0.72
    TAINMENT
    -0.65
     indisponible
    -0.61
    public
    -0.58
     AssemblyTitle
    -0.55
     public
    -0.53
    لول
    -0.52
     Bef
    -0.52
     namanya
    -0.51
     putus
    -0.51
    POSITIVE LOGITS
     Baillargeon
    0.67
     PGP
    0.64
    SPATH
    0.62
     república
    0.61
     DMT
    0.61
    rungsseite
    0.58
     Pind
    0.57
     propOrder
    0.57
     Picchu
    0.57
    krivning
    0.57
    Activations Density 0.091%

    No Known Activations