© 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. 8911
    Prev
    Next
    INDEX
    Explanations

    programming-related constructs and functions

    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
    rawDesc
    -0.71
    PostBack
    -0.67
    reactstrap
    -0.65
    RUnlock
    -0.64
     ""],
    -0.62
    NOPQRST
    -0.62
    }>;
    -0.61
    }{*}{
    -0.61
     Савезне
    -0.60
    !")
    -0.59
    POSITIVE LOGITS
     NSCoder
    0.59
     GoogleFonts
    0.55
    IonicModule
    0.54
     ill
    0.48
    fertigung
    0.46
    Portály
    0.46
    properly
    0.46
    <eos>
    0.46
    osoma
    0.45
     traction
    0.45
    Activations Density 0.056%

    No Known Activations