© 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. 14653
    Prev
    Next
    INDEX
    Explanations

    variations of the suffix "ative," indicating processes or conditions related to inflammation or medical conditions

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

    ulcerative colitis or dermatitis

    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
    addContainerGap
    -0.52
    ientôt
    -0.47
    pecabe
    -0.46
    başı
    -0.45
     CURIAM
    -0.43
     Picchu
    -0.42
    ambién
    -0.42
    rawDesc
    -0.42
    openConnection
    -0.42
    kjø
    -0.41
    POSITIVE LOGITS
    ative
    2.67
    ATIVE
    1.96
    atives
    1.66
    atively
    1.45
    ativo
    1.33
    ativa
    1.31
    ativ
    1.22
    rative
    1.21
    ulative
    1.20
    itative
    1.19
    Activations Density 0.013%

    No Known Activations