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. 10-GEMMASCOPE-RES-16K
    6. 11703
    Prev
    Next
    INDEX
    Explanations

    technical terms related to system and file management functions in programming

    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
     fratelli
    -0.84
    الب
    -0.74
    QV
    -0.74
     Jaffe
    -0.72
    apatan
    -0.68
    ANDUM
    -0.67
     canoes
    -0.67
     appuntamento
    -0.65
     compagni
    -0.65
    lindung
    -0.64
    POSITIVE LOGITS
     sys
    1.43
     Sys
    1.28
    sys
    1.27
    Sys
    1.15
    XtraGrid
    0.91
     Beards
    0.86
     SYS
    0.80
    XtraBars
    0.79
    NewGuid
    0.76
     ویکی‌پدیای
    0.75
    Activations Density 0.153%

    No Known Activations