© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 7191
    Prev
    Next
    INDEX
    Explanations

    references to physical actions or movements

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

    Following verbs like "can", "to", or "cannot"

    np_acts-logits-general · gemini-2.0-flash

    movement and passage

    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
     hosting
    -0.56
     Exacts
    -0.50
     welcoming
    -0.50
     Hosting
    -0.49
    host
    -0.49
     nakalista
    -0.49
    hosting
    -0.49
     الدولى
    -0.47
     tutup
    -0.47
     Wel
    -0.47
    POSITIVE LOGITS
     traverse
    1.11
     traversing
    0.99
     traversed
    0.99
     navigate
    0.99
     traversal
    0.96
     climb
    0.93
     navigating
    0.92
     traverses
    0.92
     navig
    0.90
     crossed
    0.88
    Activations Density 0.320%

    No Known Activations