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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 3158
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming, specifically elements of code and their structure

    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
    ябре
    -0.57
    ucap
    -0.53
    ссор
    -0.48
    ্প
    -0.48
    multer
    -0.48
     fracas
    -0.47
    سمبر
    -0.47
     pemberian
    -0.46
    vér
    -0.46
    LLocation
    -0.45
    POSITIVE LOGITS
     <!--
    3.37
    <!--
    1.50
    ><!--
    1.20
    <!--[
    0.98
     nahilalakip
    0.97
    <!--
    
    0.92
    "><!--
    0.88
     '{@
    0.86
     оригіналу
    0.82
    :✨
    0.78
    Activations Density 0.008%

    No Known Activations