Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 47504
    Prev
    Next
    INDEX
    Explanations

    references to collaborations and features between artists

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

    creative collaborations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vectorielle
    -0.52
    SourceChecksum
    -0.50
    LookAnd
    -0.46
     procedura
    -0.39
     miniaturka
    -0.38
     sécurité
    -0.38
     město
    -0.38
     mères
    -0.38
     inconvénients
    -0.37
     administratif
    -0.36
    POSITIVE LOGITS
     collaborations
    0.55
    delwed
    0.54
    Espèce
    0.51
    WriteBarrier
    0.51
     duet
    0.47
    XmlEnum
    0.47
     collaboration
    0.45
     يتيمه
    0.45
     collaborators
    0.45
     Вікіпе
    0.43
    Activations Density 0.010%

    No Known Activations