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

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 16383
    Prev
    Next
    INDEX
    Explanations

    phrases indicating distance or time related to locations

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

    followed by numbers or symbols

    np_acts-logits-general · gemini-2.0-flash

    within the paper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    MENAFN
    -0.67
    AndEndTag
    -0.61
    saraba
    -0.59
    openapi
    -0.58
     transfieras
    -0.54
    PostMapping
    -0.52
    dyti
    -0.51
    iecie
    -0.51
     jLabel
    -0.51
    internalType
    -0.51
    POSITIVE LOGITS
     walk
    1.39
     walking
    1.22
    walk
    1.15
     WALK
    1.13
    walking
    1.05
     walks
    1.04
     walked
    1.03
     Walk
    1.03
     stroll
    1.03
    Walk
    1.03
    Activations Density 0.063%

    No Known Activations