© 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. 9284
    Prev
    Next
    INDEX
    Explanations

    terms related to user experience and satisfaction improvements

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

    preceding a function or feature

    np_acts-logits-general · gemini-2.0-flash

    ways of doing things

    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
     الرياضيه
    -0.65
     propOrder
    -0.63
     استنادى
    -0.62
    RegistryLite
    -0.62
     ModelExpression
    -0.61
    ConstraintMaker
    -0.58
    RTLU
    -0.55
    ImageContext
    -0.55
    (!__
    -0.52
    sizeCache
    -0.50
    POSITIVE LOGITS
     poprzez
    0.53
     through
    0.50
     mediante
    0.45
     путем
    0.43
     möglichst
    0.43
     pamamagitan
    0.42
     by
    0.41
     mümkün
    0.41
     via
    0.40
     ASAP
    0.40
    Activations Density 0.597%

    No Known Activations