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. 10693
    Prev
    Next
    INDEX
    Explanations

    phrases related to user account management and online registration processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Creating or using an online account

    np_acts-logits-general · gemini-2.0-flash

    account registration

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    LookAnd
    -0.42
    ))->
    -0.42
    ])->
    -0.42
     Statt
    -0.41
    asties
    -0.41
    anias
    -0.40
     erb
    -0.39
    '][]
    -0.39
     marsh
    -0.39
    шков
    -0.39
    POSITIVE LOGITS
     account
    2.55
     accounts
    2.29
     Account
    2.03
    account
    2.01
     Accounts
    1.94
     ACCOUNT
    1.92
    Account
    1.78
    accounts
    1.77
    Accounts
    1.66
    ACCOUNT
    1.57
    Activations Density 0.220%

    No Known Activations