© 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. 2-GEMMASCOPE-RES-16K
    11. 6171
    Prev
    Next
    INDEX
    Explanations

    references to well-known entertainment or media companies and their associated properties

    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
    titleMargin
    -0.56
     ویکی‌پدی
    -0.55
     gyhoeddwyd
    -0.54
     ModelExpression
    -0.53
    tagext
    -0.52
     same
    -0.48
     entire
    -0.48
     '\\;'
    -0.46
     scene
    -0.46
     dieß
    -0.45
    POSITIVE LOGITS
     surla
    0.49
    ųjų
    0.40
    міст
    0.40
     України
    0.40
    omiast
    0.39
     Nachteile
    0.39
    thank
    0.36
    LookAnd
    0.36
    hdysval
    0.36
    version
    0.36
    Activations Density 1.295%

    No Known Activations