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

    Neuronpedia

    Jacobian LensNEW
    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. 0-GEMMASCOPE-RES-16K
    11. 11578
    Prev
    Next
    INDEX
    Explanations

    terms related to technical processes and operational details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <blockquote>
    -0.24
    <h4>
    -0.24
    <h3>
    -0.22
    <h6>
    -0.20
    The
    -0.18
    <h1>
    -0.17
    <h2>
    -0.17
     Defensa
    -0.17
     тогда
    -0.16
    <h5>
    -0.15
    POSITIVE LOGITS
     propOrder
    1.09
    hyrchwyd
    1.05
    UnusedPrivate
    0.97
     للاسماء
    0.94
    Hentet
    0.93
    Personendaten
    0.93
     createState
    0.91
    ﹧
    0.89
    WriteTagHelper
    0.89
    ſicht
    0.89
    Activations Density 3.943%

    No Known Activations