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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14419
    Prev
    Next
    INDEX
    Explanations

    names of people and other specific entities

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

    Bayard Dominick

    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
     $_"
    -0.80
     Hibernate
    -0.71
     $_(
    -0.71
    copg
    -0.66
     ſever
    -0.65
     Windy
    -0.65
     faſt
    -0.65
    TestUtil
    -0.65
    Moose
    -0.64
    hibernate
    -0.64
    POSITIVE LOGITS
     niew
    0.41
     pribadi
    0.39
    ichthys
    0.39
     raconter
    0.38
     Montoya
    0.38
     ogrom
    0.38
    ceğine
    0.37
     McFarland
    0.35
     detayl
    0.35
     detalles
    0.35
    Activations Density 0.347%

    No Known Activations