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. 12421
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of generation or producing something

    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
    SPATH
    -0.77
    klä
    -0.65
     griega
    -0.62
     paroi
    -0.61
    vartis
    -0.61
     nicio
    -0.60
     grecque
    -0.59
    :][
    -0.59
     tardi
    -0.58
     sockaddr
    -0.58
    POSITIVE LOGITS
     Generates
    1.46
    GENER
    1.36
     Generated
    1.32
     generators
    1.29
     Generation
    1.27
     GENER
    1.26
     generator
    1.26
     Generator
    1.24
     generation
    1.24
     generated
    1.24
    Activations Density 0.096%

    No Known Activations