© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10628
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to physical distance or separation

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

    "away"

    np_acts-logits-general · gemini-2.0-flash

    away from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.50
    Flickr
    -0.48
    Text
    -0.46
     bulletin
    -0.46
    CST
    -0.45
    хьтан
    -0.44
    PhysRev
    -0.44
    Reds
    -0.43
     Thug
    -0.43
    MessageTagHelper
    -0.43
    POSITIVE LOGITS
     Away
    1.14
     away
    1.13
     AWAY
    1.13
    Away
    1.02
    away
    1.02
    AWAY
    0.91
    eaway
    0.81
    aways
    0.67
    taway
    0.65
     awa
    0.61
    Activations Density 0.095%

    No Known Activations