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. 13889
    Prev
    Next
    INDEX
    Explanations

    contexts relating to user login and account management

    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
    TargetException
    -0.57
    HttpFoundation
    -0.46
    requestBody
    -0.45
     Uniwersyte
    -0.44
    ByteBuf
    -0.44
    igslist
    -0.42
    ربای
    -0.42
     microfilm
    -0.41
    大利
    -0.41
     blz
    -0.40
    POSITIVE LOGITS
     login
    1.70
     logged
    1.63
    login
    1.51
     Login
    1.50
    Login
    1.43
     로그
    1.42
     log
    1.41
     Log
    1.37
     Logged
    1.33
     LOGIN
    1.32
    Activations Density 0.233%

    No Known Activations