© 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. 40-GEMMASCOPE-RES-16K
    6. 1259
    Prev
    Next
    INDEX
    Explanations

    phrases related to digital privacy and user agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.56
     afterwards
    -0.44
     somebody
    -0.42
    ifikationer
    -0.42
    McGraw
    -0.41
    erdings
    -0.41
     Somebody
    -0.40
     somewhere
    -0.39
     danach
    -0.38
     Somehow
    -0.38
    POSITIVE LOGITS
    :✨
    0.50
    hoeddwyd
    0.47
    Serde
    0.43
     Vás
    0.43
     Вас
    0.43
    ChildScrollView
    0.42
    UnusedPrivate
    0.41
     мәкал
    0.41
     ROYAL
    0.40
    ⓧ
    0.40
    Activations Density 0.038%

    No Known Activations