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. 7879
    Prev
    Next
    INDEX
    Explanations

    terms related to isolation and the act of isolating

    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
     DMSO
    -0.60
     Mariner
    -0.58
     rallado
    -0.57
    PostBack
    -0.56
     Baruch
    -0.54
     cittadino
    -0.54
     Boulogne
    -0.54
     doméstico
    -0.54
     tonel
    -0.53
     trous
    -0.53
    POSITIVE LOGITS
    ValueStyle
    0.73
     isolating
    0.73
     Isolation
    0.72
    Isolation
    0.71
     autorytatywna
    0.70
     isol
    0.70
     isolation
    0.69
    esModule
    0.69
    VIAF
    0.68
     Stay
    0.67
    Activations Density 2.900%

    No Known Activations