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. 0-GEMMASCOPE-RES-16K
    6. 174
    Prev
    Next
    INDEX
    Explanations

    references and reference-related terms in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.97
     EconPapers
    -0.94
    IUrlHelper
    -0.90
    цездатний
    -0.89
    +#+#
    -0.88
     SafeMath
    -0.85
     Audiodateien
    -0.85
     DriverManager
    -0.85
    RegistryLite
    -0.84
    EndGlobalSection
    -0.84
    POSITIVE LOGITS
     van
    0.68
     followed
    0.63
    van
    0.62
    ref
    0.61
     rub
    0.61
     Group
    0.59
    REF
    0.57
     staging
    0.55
     Mor
    0.54
    事
    0.54
    Activations Density 0.221%

    No Known Activations