© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 38121
    Prev
    Next
    INDEX
    Explanations

    references to various departments within an organization

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

    department

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "}
    -0.48
    intrinsic
    -0.48
     noDo
    -0.48
     Higgs
    -0.47
    sniper
    -0.47
    parsedMessage
    -0.46
     ''}
    -0.46
     brady
    -0.46
    </>
    -0.46
    ]")]
    -0.45
    POSITIVE LOGITS
     department
    2.02
    department
    1.72
     departments
    1.63
     Department
    1.45
    Department
    1.43
     departmental
    1.35
     DEPARTMENT
    1.34
     departamento
    1.32
     Departments
    1.30
    departments
    1.29
    Activations Density 0.008%

    No Known Activations