© 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-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 11606
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to a specific type of compound or material, particularly those associated with indium

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.95
     Roskov
    -0.94
    StoreMessageInfo
    -0.94
     متعلقه
    -0.93
     ainfi
    -0.91
     ―――――
    -0.90
    SourceChecksum
    -0.90
     myſelf
    -0.88
     faſt
    -0.86
     betweenstory
    -0.86
    POSITIVE LOGITS
    Ind
    1.14
     Ind
    0.95
    IND
    0.88
    ind
    0.85
     IND
    0.82
     ind
    0.82
    lice
    0.67
    核
    0.65
     pre
    0.65
     Endor
    0.65
    Activations Density 0.064%

    No Known Activations