© 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. 36-GEMMASCOPE-RES-16K
    11. 6320
    Prev
    Next
    INDEX
    Explanations

    phrases and functions related to folder management operations in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suaminya
    -0.55
    <strong>
    -0.52
    <em>
    -0.46
    <b>
    -0.41
     brasileño
    -0.41
     istrinya
    -0.40
     Freundin
    -0.40
    <i>
    -0.40
     conmigo
    -0.40
     keluarganya
    -0.39
    POSITIVE LOGITS
     stuff
    0.81
     Chwiliwch
    0.66
     للمعارف
    0.64
     basic
    0.60
     guy
    0.60
     shit
    0.60
     stuffs
    0.59
     we
    0.59
     necessary
    0.58
     our
    0.58
    Activations Density 0.663%

    No Known Activations