© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 12002
    Prev
    Next
    INDEX
    Explanations

    specific components and combinations in chemical formulations or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ionales
    -0.44
    consulté
    -0.43
    anguera
    -0.42
     Lokales
    -0.42
    antle
    -0.42
    zos
    -0.38
     halla
    -0.38
    ister
    -0.38
    ioneer
    -0.38
     jos
    -0.38
    POSITIVE LOGITS
     thereof
    2.58
     thereon
    2.19
     thereto
    2.09
     therein
    2.05
     therefrom
    2.00
     therewith
    1.95
     therefor
    1.59
     thereunder
    1.59
     hereof
    1.45
     thereupon
    1.44
    Activations Density 1.008%

    No Known Activations