© 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
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15699
    Prev
    Next
    INDEX
    Explanations

    the presence of various formatting tags or structural elements in the text

    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
    Jeografia
    -0.52
    RoomId
    -0.52
    colgante
    -0.50
    puerta
    -0.47
     enfans
    -0.47
     bénéfices
    -0.47
     Valentín
    -0.46
    Legături
    -0.46
    ensaft
    -0.46
    SBATCH
    -0.46
    POSITIVE LOGITS
    <h2>
    0.93
    <h3>
    0.86
    <h1>
    0.84
    <h4>
    0.84
    <h5>
    0.72
    <h6>
    0.57
    /**
    0.55
    <bos>
    0.51
    __*/
    0.47
     Перейти
    0.45
    Activations Density 0.047%

    No Known Activations