© 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. 15-GEMMASCOPE-RES-16K
    11. 4985
    Prev
    Next
    INDEX
    Explanations

    specific references to financial entities and transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eſ
    -0.46
    estay
    -0.42
     ſever
    -0.42
     unſ
    -0.40
     houſe
    -0.39
    avaş
    -0.38
    funeral
    -0.37
     razie
    -0.37
    errHandler
    -0.36
     contextLoads
    -0.36
    POSITIVE LOGITS
     AssemblyCompany
    0.63
     kasarigan
    0.60
    Personensuche
    0.54
     nakalista
    0.52
    AndEndTag
    0.49
    thenReturn
    0.48
     Administrativna
    0.46
    ExecuteReader
    0.46
    ContentAlignment
    0.44
    iocene
    0.44
    Activations Density 1.539%

    No Known Activations