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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8814
    Prev
    Next
    INDEX
    Explanations

    terms related to administrative actions and procedures

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

    the word "administration" or "admin"

    np_acts-logits-general · gemini-2.0-flash

    admin administration and relatedness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HTT
    -0.55
     Larson
    -0.55
    ToTensor
    -0.54
     Martyr
    -0.54
    OURCE
    -0.51
    forsk
    -0.51
     endorsement
    -0.51
    ilent
    -0.50
     Depp
    -0.50
     endorsements
    -0.50
    POSITIVE LOGITS
    ModelAdmin
    1.11
    admins
    1.03
     administrators
    1.01
     Admin
    1.00
     ADMIN
    0.98
     ADM
    0.95
    administ
    0.93
     admins
    0.90
     Administ
    0.89
     administration
    0.89
    Activations Density 0.089%

    No Known Activations