© 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. 30-GEMMASCOPE-RES-16K
    11. 9852
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to file operations and data handling

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

    Code referring to source or destination

    np_acts-logits-general · gemini-2.0-flash

    source or destination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulement
    -0.29
    
    -0.29
     Octubre
    -0.29
    нительно
    -0.29
    liament
    -0.28
     Kø
    -0.28
    spreis
    -0.27
     hecho
    -0.27
     Baw
    -0.27
     kiến
    -0.26
    POSITIVE LOGITS
     destination
    1.57
     source
    1.38
     Destination
    1.34
    destination
    1.30
    Destination
    1.24
     dest
    1.23
     target
    1.21
     SOURCE
    1.16
     Source
    1.14
     destinations
    1.14
    Activations Density 0.965%

    No Known Activations