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. 12201
    Prev
    Next
    INDEX
    Explanations

    details related to luxurious residential properties and their features

    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
    fromnode
    -0.64
    قایناقلار
    -0.60
    Népesség
    -0.58
     billig
    -0.57
    ništ
    -0.54
     cheaply
    -0.54
    رشف
    -0.54
    Rooms
    -0.53
     poveznice
    -0.53
     motel
    -0.53
    POSITIVE LOGITS
    IBAction
    0.70
     custom
    0.67
     wine
    0.61
     FetchType
    0.56
     bespoke
    0.55
    custom
    0.52
    #
    0.51
     customized
    0.50
     dramatic
    0.50
     customised
    0.49
    Activations Density 0.032%

    No Known Activations