© 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. 60796
    Prev
    Next
    INDEX
    Explanations

    terms and cultural references specific to Jewish heritage and traditions

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

    Yiddish surnames ending in -baum, -witz, -man

    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
    inWeight
    -0.48
    sidemargin
    -0.45
     pulumi
    -0.45
     الحره
    -0.43
    ⅘
    -0.41
     shutil
    -0.39
    жнему
    -0.39
    kadot
    -0.39
     désert
    -0.38
     للاسماء
    -0.38
    POSITIVE LOGITS
     Yiddish
    0.51
    urlpatterns
    0.43
     "..\..\
    0.41
     resourceCulture
    0.40
    complexType
    0.40
    prenom
    0.39
    цездатний
    0.37
    lectual
    0.37
     AssemblyVersion
    0.36
    Дереккөздер
    0.36
    Activations Density 0.032%

    No Known Activations