© 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. 24-GEMMASCOPE-RES-16K
    11. 8674
    Prev
    Next
    INDEX
    Explanations

    specific terms related to data processing and programming tasks

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

    Comes before articles (a, an) or prepositions (on, to, about)

    np_acts-logits-general · gemini-2.0-flash

    technical terms and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.50
     Aid
    -0.33
    BeginInit
    -0.33
    .
    -0.32
    +#+#
    -0.32
     arran
    -0.31
    
    -0.31
     Hope
    -0.31
     verdient
    -0.31
    出版年
    -0.31
    POSITIVE LOGITS
    ſelf
    0.53
    Pyx
    0.51
     متحده
    0.49
     MainAxisSize
    0.47
    chartInstance
    0.47
    UVWXYZ
    0.46
    mnop
    0.45
     ſtre
    0.45
     ModelExpression
    0.45
     judo
    0.44
    Activations Density 0.750%

    No Known Activations