© 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. 41-GEMMASCOPE-RES-16K
    6. 12950
    Prev
    Next
    INDEX
    Explanations

    interactions and processes related to communication and fulfillment in a logistical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.55
     Normdatei
    -0.54
    NameInMap
    -0.47
     resourceCulture
    -0.47
     informée
    -0.43
    jenost
    -0.43
    CppMethod
    -0.42
    testens
    -0.39
    Pyx
    -0.39
    AnchorTagHelper
    -0.39
    POSITIVE LOGITS
     directly
    3.53
     direct
    3.39
    directly
    3.14
     Directly
    3.08
    Direct
    2.95
    direct
    2.91
    直接
    2.89
     directement
    2.84
     directamente
    2.81
     DIRECT
    2.78
    Activations Density 1.425%

    No Known Activations