© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 2795
    Prev
    Next
    INDEX
    Explanations

    terms related to data packets and their transmission status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.45
     surla
    -0.44
    currentColor
    -0.43
     useState
    -0.42
    tableFuture
    -0.40
    JEL
    -0.38
    IntoConstraints
    -0.38
    useState
    -0.38
    featureID
    -0.37
     ArrayAdapter
    -0.37
    POSITIVE LOGITS
    MemoryWarning
    0.62
     Receiving
    0.61
     Receive
    0.60
    Receiving
    0.59
     receive
    0.59
     recevoir
    0.57
    receive
    0.56
    Receive
    0.56
     RECEIVE
    0.54
     receives
    0.54
    Activations Density 0.148%

    No Known Activations