© 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
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 9708
    Prev
    Next
    INDEX
    Explanations

    references to singular entities or concepts within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Initializable
    -0.45
     ब्रेकडाउन
    -0.39
     někter
    -0.37
    FieldDescriptor
    -0.37
    
    -0.36
    setupUi
    -0.35
    Outro
    -0.35
    Aiheesta
    -0.35
    Etimología
    -0.35
     quelque
    -0.35
    POSITIVE LOGITS
     single
    2.98
    single
    2.59
     SINGLE
    2.30
    Single
    2.28
     Single
    2.27
    SINGLE
    2.11
     tunggal
    1.99
     singola
    1.83
     singolo
    1.71
    单
    1.70
    Activations Density 1.875%

    No Known Activations