© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1027
    Prev
    Next
    INDEX
    Explanations

    references to series, particularly in a context related to guides or studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "series"

    np_acts-logits-general · gemini-2.0-flash

    series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IfNot
    -0.47
     Philanth
    -0.45
    Tob
    -0.45
    Chimp
    -0.44
    Gud
    -0.44
     Tramp
    -0.43
    alipay
    -0.43
     Toast
    -0.43
     Gib
    -0.43
    thschild
    -0.43
    POSITIVE LOGITS
     series
    2.42
     Series
    2.20
    Series
    2.19
     SERIES
    2.16
    series
    2.16
    SERIES
    1.92
     série
    1.74
     serie
    1.73
     séries
    1.72
    iseries
    1.63
    Activations Density 0.103%

    No Known Activations