© 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. 2312
    Prev
    Next
    INDEX
    Explanations

    descriptions of mechanical or functional interactions in a technical context

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

    Prepositions followed by articles

    np_acts-logits-general · gemini-2.0-flash

    prepositions of placement and direction

    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
    ViewImports
    -0.72
    ########.
    -0.68
    erialization
    -0.58
    CloseOperation
    -0.57
    CppCodeGen
    -0.54
    uestamente
    -0.54
    INCREF
    -0.53
    hyrchwyd
    -0.51
     dieſen
    -0.51
    citep
    -0.50
    POSITIVE LOGITS
    RenderAtEndOf
    0.43
     jadx
    0.32
     kiệm
    0.31
    IUrlHelper
    0.30
     stages
    0.29
     doprav
    0.29
    TypedDataSet
    0.29
    autaire
    0.28
     pož
    0.28
     position
    0.28
    Activations Density 0.585%

    No Known Activations