Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15717
    Prev
    Next
    INDEX
    Explanations

    terms related to coordination and organization of activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Depp
    -0.82
     Sall
    -0.67
     uVar
    -0.67
    vaux
    -0.66
     plais
    -0.65
    BeforeClass
    -0.64
    hesda
    -0.64
    s
    -0.62
    ِل
    -0.62
    LoadScene
    -0.60
    POSITIVE LOGITS
     Coordinates
    1.18
     coordinates
    1.16
    Coordinates
    1.13
     Coordinate
    1.10
     coordination
    1.06
     coord
    1.06
     coordinate
    1.05
     COORDIN
    1.04
    ordinating
    1.03
     coordinating
    1.03
    Activations Density 0.090%

    No Known Activations