© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 11367
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or names, particularly in a context related to investment or financial markets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.65
     AssemblyCulture
    -0.55
     ſte
    -0.54
     juſ
    -0.51
     pleaſure
    -0.50
     ſtand
    -0.49
     poffible
    -0.48
     juſt
    -0.47
     itſelf
    -0.46
     ſta
    -0.46
    POSITIVE LOGITS
    eri
    1.66
    era
    1.63
    ery
    1.49
    ering
    1.45
    eren
    1.41
    ERI
    1.41
    ero
    1.40
    ere
    1.40
    eras
    1.39
    ERA
    1.38
    Activations Density 0.595%

    No Known Activations