© 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. 22-GEMMASCOPE-RES-16K
    11. 3878
    Prev
    Next
    INDEX
    Explanations

    permissions and access control issues related to user accounts and system administration

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

    Permissions or roles

    np_acts-logits-general · gemini-2.0-flash

    user role and permission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    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
    -0.54
    romyal
    -0.53
    Convergence
    -0.53
    ">:
    -0.50
    ագրություններ
    -0.49
     Convergence
    -0.49
     discontinuous
    -0.49
     تانيه
    -0.49
     discontinuities
    -0.48
    ponses
    -0.47
    POSITIVE LOGITS
     permission
    1.54
     permissions
    1.50
     Permission
    1.33
    Permission
    1.28
     Permissions
    1.27
    permission
    1.26
     role
    1.18
     roles
    1.17
     Role
    1.17
     privileges
    1.15
    Activations Density 0.393%

    No Known Activations