© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13544
    Prev
    Next
    INDEX
    Explanations

    transformative changes that impact societal structures and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Photocase
    -0.52
    ثيق
    -0.46
    PropertyChanging
    -0.44
    出版年
    -0.43
     Italijanski
    -0.43
     kasarigan
    -0.43
    Collegamenti
    -0.43
     ModelExpression
    -0.41
    GIVEREF
    -0.41
    RTLU
    -0.41
    POSITIVE LOGITS
    didSet
    0.46
    zzleHttp
    0.39
     Hinsicht
    0.36
    kook
    0.35
    getMinutes
    0.35
     mał
    0.35
    giphy
    0.34
     reservado
    0.34
     يتيمه
    0.34
     titolata
    0.34
    Activations Density 0.317%

    No Known Activations