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. 5-GEMMASCOPE-RES-16K
    6. 4475
    Prev
    Next
    INDEX
    Explanations

    specific keywords related to software and development processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     públicos
    -0.46
     mạnh
    -0.37
     conç
    -0.37
    boca
    -0.36
     ubicada
    -0.36
     veřej
    -0.36
    strong
    -0.36
     público
    -0.35
    OUBLE
    -0.34
     mặt
    -0.34
    POSITIVE LOGITS
    SourceChecksum
    1.79
     ModelExpression
    1.69
    ✨:
    1.46
    fjspx
    1.44
    verwijspagina
    1.40
     &___
    1.32
    NameInMap
    1.30
     CreateTagHelper
    1.27
     ویکی‌پدیا
    1.26
     autorytatywna
    1.25
    Activations Density 0.364%

    No Known Activations