© 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. 34-GEMMASCOPE-RES-16K
    11. 222
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific investigation and research methodologies, particularly in the context of analyzing substances and their properties

    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
     execution
    -0.40
     ditemp
    -0.35
     inaugu
    -0.34
     realis
    -0.34
     desenli
    -0.34
     Executed
    -0.34
     розмі
    -0.34
     comfortable
    -0.32
    portál
    -0.32
     handover
    -0.32
    POSITIVE LOGITS
     chemically
    0.99
     mixtures
    0.91
     additives
    0.88
     formulations
    0.85
     ingredient
    0.82
     ingredients
    0.81
     commercially
    0.80
     impurities
    0.79
     purity
    0.78
    ingredients
    0.77
    Activations Density 0.886%

    No Known Activations