© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 116387
    Prev
    Next
    INDEX
    Explanations

    phrases related to authorization and official permissions

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

    authorization and authorized actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Vedi
    -0.51
     Economía
    -0.42
     recensement
    -0.41
     Económica
    -0.39
     Ведь
    -0.38
     gidi
    -0.38
     iklan
    -0.38
    s
    -0.37
     Moscú
    -0.37
    KommentareTeilen
    -0.36
    POSITIVE LOGITS
     authorization
    1.09
     Authorization
    1.04
     Autorizaciones
    0.98
     authorize
    0.93
     authorized
    0.91
     Autorisations
    0.90
    Authorization
    0.88
    authorize
    0.87
     authorisation
    0.86
     Authorized
    0.85
    Activations Density 0.007%

    No Known Activations