© 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. 28-GEMMASCOPE-RES-16K
    11. 10064
    Prev
    Next
    INDEX
    Explanations

    details about physical features and specifications of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after "with" relating to closures or attachment

    np_acts-logits-general · gemini-2.0-flash

    zipper fasteners and closures

    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
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.49
     saveiro
    -0.49
     Meksi
    -0.46
    -------------</
    -0.46
    ########.
    -0.45
     pravi
    -0.44
     pères
    -0.44
     églises
    -0.44
    AnchorTagHelper
    -0.43
    BufferException
    -0.43
    POSITIVE LOGITS
     buttons
    0.62
     handles
    0.58
     hinges
    0.52
     himo
    0.52
     screws
    0.52
     laces
    0.52
     removable
    0.50
     caps
    0.49
     closure
    0.49
     rope
    0.49
    Activations Density 0.475%

    No Known Activations