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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 3034
    Prev
    Next
    INDEX
    Explanations

    lines of code related to conditional statements and error handling

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

    Code-related terms or snippets

    np_acts-logits-general · gemini-2.0-flash

    programming statements and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.56
     potentially
    -0.54
    potentially
    -0.53
     CanadaChoose
    -0.51
    Searcher
    -0.51
     wich
    -0.51
    idered
    -0.50
    JsonHelper
    -0.49
     Ibidem
    -0.48
     useCallback
    -0.48
    POSITIVE LOGITS
     HasFactory
    0.82
    riwal
    0.75
     lakhs
    0.70
     ferons
    0.69
     venons
    0.68
     irrespective
    0.68
     defaultstate
    0.67
     Maruti
    0.67
    setBounds
    0.65
     upto
    0.65
    Activations Density 0.064%

    No Known Activations