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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14289
    Prev
    Next
    INDEX
    Explanations

    references to navigational tools and instruments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    directions or navigation

    np_acts-logits-general · gemini-2.0-flash

    navigation and directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.55
     createState
    -0.51
    tagHelperRunner
    -0.49
    ReusableCell
    -0.44
    antMatchers
    -0.44
    ContentAsync
    -0.44
     AssemblyProduct
    -0.44
     dessous
    -0.41
    RunAsync
    -0.40
     Modèle
    -0.39
    POSITIVE LOGITS
     directions
    1.71
     navigation
    1.65
     guide
    1.60
     guides
    1.51
     navig
    1.49
     guiding
    1.47
     navigate
    1.46
     navigational
    1.46
    directions
    1.44
     navigating
    1.43
    Activations Density 0.341%

    No Known Activations