© 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 EvalsExportsAPI 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. 36042
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations, particularly those related to organizations or military titles

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

    USS and Russ prefixes

    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
    NSIndexPath
    -0.55
    inguém
    -0.50
    뀐
    -0.47
     IndexPath
    -0.46
     pouvoit
    -0.44
    뀜
    -0.44
     feroit
    -0.44
     étoit
    -0.43
     gebra
    -0.43
    CommonModule
    -0.43
    POSITIVE LOGITS
    uss
    2.97
    USS
    2.25
    uß
    1.59
    usses
    1.28
    usse
    1.26
    Puss
    1.20
     USS
    1.11
    ussen
    1.11
     Russ
    1.04
    ussa
    1.01
    Activations Density 0.003%

    No Known Activations