© 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. 18-GEMMASCOPE-RES-16K
    11. 2905
    Prev
    Next
    INDEX
    Explanations

    mentions of staff or personnel

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

    "staff" followed by various words

    np_acts-logits-general · gemini-2.0-flash

    staff followed by roles or members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.78
    
    -0.73
     Grom
    -0.64
     XCTest
    -0.63
     Pase
    -0.63
    webElementXpaths
    -0.63
    Rien
    -0.62
     Arie
    -0.61
    itere
    -0.61
     tol
    -0.60
    POSITIVE LOGITS
     members
    1.05
     staffs
    0.93
     staff
    0.92
    members
    0.88
    Staff
    0.87
     Staff
    0.85
    staff
    0.85
     member
    0.82
     STAFF
    0.76
     Members
    0.76
    Activations Density 0.052%

    No Known Activations