© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 910
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to energy and chemical properties

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Mathematical or symbolic expressions

    np_acts-logits-general · gemini-2.0-flash

    another similarly equally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ArrowToggle
    -0.47
    AutoScaleMode
    -0.44
     getItem
    -0.44
     invokingState
    -0.41
    endphp
    -0.41
    NameInMap
    -0.40
     ComVisible
    -0.40
     betweenstory
    -0.39
     AppCompatTheme
    -0.39
    Geplaatst
    -0.39
    POSITIVE LOGITS
     another
    0.58
     similarly
    0.55
    Another
    0.50
    อีก
    0.50
    同样
    0.50
    同じく
    0.49
     dejen
    0.49
    同樣
    0.48
    chargez
    0.47
     equally
    0.47
    Activations Density 3.768%

    No Known Activations