© 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. 21-GEMMASCOPE-RES-16K
    11. 11901
    Prev
    Next
    INDEX
    Explanations

    aspects related to medical or pharmaceutical topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.47
    SourceChecksum
    -0.47
     />
    -0.46
    NameInMap
    -0.44
    VYMaps
    -0.44
     @"/
    -0.43
     esternos
    -0.43
    Cyfeiriadau
    -0.43
    tagHelperRunner
    -0.43
     الحره
    -0.43
    POSITIVE LOGITS
     comunicarse
    0.44
    essentiel
    0.44
    expliquer
    0.41
    1
    0.40
     verrez
    0.40
    .
    0.39
     nôtre
    0.39
    PS
    0.39
    ps
    0.39
    extérieur
    0.38
    Activations Density 0.160%

    No Known Activations