© 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. 12-GEMMASCOPE-RES-16K
    6. 6188
    Prev
    Next
    INDEX
    Explanations

    key terms and structures related to XML or data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.46
    principalColumn
    -0.35
    SafeMath
    -0.34
     diyor
    -0.33
    gungen
    -0.31
    waitKey
    -0.29
     sectores
    -0.28
     žem
    -0.28
     domov
    -0.28
     miatt
    -0.28
    POSITIVE LOGITS
    UnusedPrivate
    0.61
    httphttps
    0.60
    complexContent
    0.60
    InjectAttribute
    0.59
    LabelTagHelper
    0.59
    WithIOException
    0.59
    Clik
    0.58
    </thead>
    0.58
     SqlCommand
    0.58
    casian
    0.58
    Activations Density 0.440%

    No Known Activations