© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 8954
    Prev
    Next
    INDEX
    Explanations

    terms related to navigation systems and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matchCondition
    -0.89
    
    -0.81
    RTHOOK
    -0.80
    SBATCH
    -0.80
    MeasureSpec
    -0.79
     sympy
    -0.78
    shakes
    -0.76
     mCurrent
    -0.75
    -------
    -0.74
    iastes
    -0.73
    POSITIVE LOGITS
     navigation
    1.30
    nav
    1.26
     nav
    1.25
     Navigation
    1.24
     NAV
    1.23
    Nav
    1.17
     navigate
    1.16
    NAV
    1.16
     navig
    1.15
    Navigation
    1.10
    Activations Density 0.305%

    No Known Activations