© 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. 13031
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to processes and operations in scientific and engineering contexts

    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
    knew
    -0.37
    OrNil
    -0.36
     étoit
    -0.31
     pouvoit
    -0.31
     demand
    -0.31
    ToAdd
    -0.30
     uſe
    -0.30
     groundwater
    -0.30
    omock
    -0.30
    näm
    -0.30
    POSITIVE LOGITS
     repaired
    1.36
     recovered
    1.30
     cleaned
    1.26
     cleansed
    1.26
     restored
    1.25
     freshly
    1.23
     newly
    1.23
     transformed
    1.20
     renovated
    1.18
     remodeled
    1.14
    Activations Density 2.048%

    No Known Activations