© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11282
    Prev
    Next
    INDEX
    Explanations

    references to common coding practices and conventions

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

    "common" or "cmn" (abbreviations)

    np_acts-logits-general · gemini-2.0-flash

    common

    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
    TypedDataSet
    -0.70
    ynb
    -0.62
    IntoConstraints
    -0.57
    TagMode
    -0.51
    tanleria
    -0.51
    awtextra
    -0.50
     ModelExpression
    -0.50
    󠁢
    -0.49
    EndContext
    -0.48
    SequentialGroup
    -0.47
    POSITIVE LOGITS
    common
    1.11
    Common
    0.97
     Common
    0.95
    COMMON
    0.84
     common
    0.83
     COMMON
    0.81
    共通
    0.75
    通用
    0.71
    misc
    0.69
     algemene
    0.69
    Activations Density 0.377%

    No Known Activations