© 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. 6472
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the structure or breakdown of processes and categories

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

    Followed by numbers (two, three)

    np_acts-logits-general · gemini-2.0-flash

    two or three categories/steps

    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
     ?>/
    -0.47
     unknownFields
    -0.45
    __*/
    -0.44
    verwijspagina
    -0.41
    IsMutable
    -0.38
     ControllerBase
    -0.38
     souri
    -0.38
    árbol
    -0.37
    tifact
    -0.37
    moreland
    -0.36
    POSITIVE LOGITS
     main
    0.87
    主要
    0.77
     primarily
    0.72
     mainly
    0.71
     principal
    0.71
     principale
    0.70
     utama
    0.69
     principally
    0.68
     principales
    0.66
     basic
    0.66
    Activations Density 0.357%

    No Known Activations