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. 20-GEMMASCOPE-RES-16K
    6. 12790
    Prev
    Next
    INDEX
    Explanations

    contexts involving work, labor, or employment-related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ProtoMessage
    -0.63
    τητα
    -0.55
     DialogInterface
    -0.52
     tromper
    -0.51
     جمله
    -0.51
     Италијани
    -0.50
    хьтан
    -0.49
     unknownFields
    -0.49
     "..\..\..\
    -0.49
    というもの
    -0.48
    POSITIVE LOGITS
     that
    0.76
     whose
    0.76
     of
    0.68
     deemed
    0.67
     resembling
    0.64
     already
    0.63
     ranging
    0.60
     beyond
    0.60
     requiring
    0.60
     consisting
    0.59
    Activations Density 1.575%

    No Known Activations