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. 21-GEMMASCOPE-RES-16K
    6. 390
    Prev
    Next
    INDEX
    Explanations

    verb forms associated with various activities, particularly in contexts relating to media production and research tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.94
    ChildScrollView
    -0.88
    DoubleQuotes
    -0.86
    +#+#
    -0.85
     AssemblyCulture
    -0.81
    sizeCache
    -0.74
    ISupport
    -0.74
    Personendaten
    -0.71
    Geplaatst
    -0.71
     protoimpl
    -0.69
    POSITIVE LOGITS
     them
    0.62
     anything
    0.62
    下去
    0.59
     without
    0.55
     Vordergrund
    0.54
    เอง
    0.54
    using
    0.54
     ulang
    0.52
    pygame
    0.52
    spesies
    0.51
    Activations Density 0.857%

    No Known Activations