© 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. 20-GEMMASCOPE-RES-16K
    11. 4409
    Prev
    Next
    INDEX
    Explanations

    mentions of security permissions and access controls

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

    Permissions, rights, and access control

    np_acts-logits-general · gemini-2.0-flash

    permissions and access control

    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
    UnknownFieldSet
    -0.69
    ValueStyle
    -0.62
     discontinuous
    -0.56
    ">:
    -0.53
    ագրություններ
    -0.52
    TagHelpers
    -0.52
     ModelExpression
    -0.52
    PerformLayout
    -0.51
     παρά
    -0.50
     تانيه
    -0.50
    POSITIVE LOGITS
     permissions
    0.97
     admin
    0.97
     permission
    0.93
     privileges
    0.90
    admin
    0.88
     Admin
    0.88
     administrator
    0.84
     administrative
    0.84
     access
    0.82
     ADMIN
    0.82
    Activations Density 0.331%

    No Known Activations