© 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. 12-GEMMASCOPE-RES-16K
    11. 3024
    Prev
    Next
    INDEX
    Explanations

    non-text content, particularly HTML and LaTeX formatting

    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
    ViewFeatures
    -0.38
    jface
    -0.36
    nmgp
    -0.36
     Jar
    -0.36
    automatic
    -0.35
     kasarigan
    -0.35
     quoting
    -0.35
     InputDecoration
    -0.35
     duquel
    -0.35
    뀜
    -0.35
    POSITIVE LOGITS
     виправивши
    0.70
    bootstrapcdn
    0.66
     betweenstory
    0.54
     '\\;'
    0.52
    LEncoder
    0.50
     [*]
    0.49
     Offisielt
    0.49
    urably
    0.48
    </th>
    0.47
    Microkernel
    0.47
    Activations Density 2.003%

    No Known Activations