© 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. 7-GEMMASCOPE-RES-16K
    6. 14817
    Prev
    Next
    INDEX
    Explanations

    formatted strings or code, specifically those that begin with a tag or a specified prefix

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     explosión
    -0.52
     Audiodateien
    -0.49
     corrupción
    -0.48
     violación
    -0.48
     proporción
    -0.44
     orilla
    -0.44
     Wikispecies
    -0.44
    transQ
    -0.44
     vermelhas
    -0.43
     iub
    -0.42
    POSITIVE LOGITS
     protoimpl
    0.55
    RTLR
    0.50
     ostavi
    0.49
     autorytatywna
    0.48
    MarshalTo
    0.46
    <bos>
    0.46
    ftagPool
    0.45
    Gira
    0.43
    httphttps
    0.42
    Externe
    0.41
    Activations Density 0.632%

    No Known Activations