Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 1944
    Prev
    Next
    INDEX
    Explanations

    percentages and numerical data related to various statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.57
    ibatis
    -0.55
    baomidou
    -0.53
    RegistryLite
    -0.52
     Italijanski
    -0.51
    getMenuInflater
    -0.50
    djangoproject
    -0.50
    )]=
    -0.49
     ddelweddau
    -0.49
    WebMethod
    -0.48
    POSITIVE LOGITS
     accounted
    1.60
     accounts
    1.59
     account
    1.57
     accounting
    1.43
    account
    1.39
     ACCOUNT
    1.39
     Account
    1.37
    accounts
    1.35
     Accounts
    1.34
    accounting
    1.31
    Activations Density 0.527%

    No Known Activations