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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 6471
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to navigation systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     via
    -0.69
     onCreateView
    -0.62
     Via
    -0.62
     betweenstory
    -0.59
     devriez
    -0.57
    erent
    -0.56
    Via
    -0.56
    somewhere
    -0.53
    FormTagHelper
    -0.53
    endregion
    -0.53
    POSITIVE LOGITS
    navigation
    1.43
    Navigation
    1.37
     navigation
    1.34
     Navigation
    1.31
     NAVIGATION
    1.01
    NAVIGATION
    0.95
     Navig
    0.93
    navig
    0.91
     navigational
    0.89
    Navig
    0.88
    Activations Density 0.102%

    No Known Activations