© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 8677
    Prev
    Next
    INDEX
    Explanations

    terms related to navigation and navigating through complex environments

    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
    CardModule
    -0.77
     Xunit
    -0.76
    TemporalType
    -0.76
    ostante
    -0.73
    ekyll
    -0.72
     idéia
    -0.72
    #+#
    -0.70
    memberOf
    -0.68
    pleaños
    -0.68
    paña
    -0.67
    POSITIVE LOGITS
    navigate
    1.14
     navig
    1.08
     navigate
    1.01
     navigating
    1.00
     navigation
    0.95
    )
    0.95
    navig
    0.93
     useNavigate
    0.90
     Navigate
    0.87
    multirow
    0.84
    Activations Density 0.087%

    No Known Activations