© 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 EvalsExportsinterp-engineNEWAPI 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. 1963
    Prev
    Next
    INDEX
    Explanations

    hex color codes and their related attributes

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

    "Western" or "western Europe"

    np_acts-logits-general · gemini-2.0-flash

    Western locations and studies

    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
    AddTagHelper
    -0.81
    StoryboardSegue
    -0.79
    featureID
    -0.77
     propOrder
    -0.71
    ########.
    -0.70
    WireFormatLite
    -0.68
     NSCoder
    -0.66
    GEBURTSDATUM
    -0.64
    +#+#
    -0.63
    rungsseite
    -0.62
    POSITIVE LOGITS
     Western
    0.45
    ene
    0.44
     der
    0.44
     Der
    0.41
     James
    0.39
     Fore
    0.37
     western
    0.37
    Western
    0.37
     Herbert
    0.36
    ley
    0.36
    Activations Density 0.089%

    No Known Activations