© 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. 10-GEMMASCOPE-RES-16K
    11. 10640
    Prev
    Next
    INDEX
    Explanations

    escape characters and formatting symbols, particularly in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thâu
    -0.72
    Rival
    -0.59
     Geraadpleegd
    -0.58
    lujah
    -0.55
    lanze
    -0.54
    דש
    -0.53
     himo
    -0.52
    után
    -0.51
    אני
    -0.51
    المكان
    -0.51
    POSITIVE LOGITS
    StoreMessageInfo
    0.72
     NSCoder
    0.65
    tabular
    0.61
    WebVitals
    0.60
    spół
    0.60
    Autoritní
    0.57
    asgi
    0.55
    AllowUser
    0.54
    hline
    0.54
    </thead>
    0.54
    Activations Density 0.023%

    No Known Activations