© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 5083
    Prev
    Next
    INDEX
    Explanations

    information related to personal identification and user credentials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVEREF
    -0.79
     تضيفلها
    -0.62
    tagHelperRunner
    -0.58
     wireType
    -0.56
     trône
    -0.55
    modelBuilder
    -0.55
    DockStyle
    -0.54
    Портал
    -0.51
    elemField
    -0.50
    BeginContext
    -0.50
    POSITIVE LOGITS
     name
    1.08
     names
    0.99
     contact
    0.91
     address
    0.88
     username
    0.81
     addresses
    0.79
     usernames
    0.78
     phone
    0.76
     details
    0.72
     initials
    0.71
    Activations Density 0.423%

    No Known Activations