Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10378
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and representations in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Abbreviations starting with "T"

    np_acts-logits-general · gemini-2.0-flash

    acronyms and abbreviations starting with T

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.65
    ⓧ
    -0.55
    PerformLayout
    -0.54
     noDo
    -0.53
     виправивши
    -0.53
    DockStyle
    -0.51
    reportWebVitals
    -0.49
     Савезне
    -0.49
     للاسماء
    -0.49
    úgó
    -0.49
    POSITIVE LOGITS
     TC
    1.14
     T
    1.11
     TP
    1.10
     TD
    1.10
     TB
    1.08
     TN
    1.08
     TM
    1.06
     TG
    1.05
     TT
    1.05
     TS
    1.04
    Activations Density 2.748%

    No Known Activations