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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15573
    Prev
    Next
    INDEX
    Explanations

    elements describing simplicity and minimalism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     estekak
    -0.69
    findpost
    -0.57
    MLLoader
    -0.56
     resourceCulture
    -0.51
    adaptiveStyles
    -0.49
     ErrIntOverflow
    -0.46
    flashdata
    -0.45
    ifiquement
    -0.45
     يتيمه
    -0.44
     FetchType
    -0.44
    POSITIVE LOGITS
     minimalist
    0.83
    シンプル
    0.78
     simplicity
    0.78
     minimalistic
    0.75
    シンプルな
    0.75
     simple
    0.73
     minimalis
    0.72
     plain
    0.69
     basic
    0.69
    simple
    0.67
    Activations Density 0.544%

    No Known Activations