© 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. 13467
    Prev
    Next
    INDEX
    Explanations

    structured code elements and key programming constructs such as conditional statements and method definitions

    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
     (
    -0.62
     "
    -0.56
    (
    -0.54
    the
    -0.53
     or
    -0.51
     及
    -0.50
    oni
    -0.50
     suces
    -0.49
    ,
    -0.49
     el
    -0.49
    POSITIVE LOGITS
    expandindo
    1.35
     Normdatei
    1.21
     الحره
    1.03
     مرئيه
    1.00
     Audiodateien
    0.97
     ویکی‌پدی
    0.95
    ंदीखरीदारी
    0.93
     дописавши
    0.92
     الاطلاع
    0.92
    
    0.88
    Activations Density 0.032%

    No Known Activations