© 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. 20-GEMMASCOPE-RES-16K
    11. 15419
    Prev
    Next
    INDEX
    Explanations

    references to election-related discussions or decisions

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

    Follows verbs of request or permission

    np_acts-logits-general · gemini-2.0-flash

    legal and administrative actions

    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
     CreateTagHelper
    -0.77
    DockStyle
    -0.74
    Архівовано
    -0.65
     disponibilités
    -0.60
    WindowConstants
    -0.60
     createState
    -0.60
     समीक्षाएं
    -0.58
    ReusableCell
    -0.56
     mellitus
    -0.54
    quelize
    -0.52
    POSITIVE LOGITS
     necessary
    0.61
     SafeMath
    0.57
    Necessary
    0.56
    contentLoaded
    0.56
    ConfigureAwait
    0.54
    canestro
    0.53
     Necessary
    0.53
     кӀ
    0.52
     needful
    0.51
     details
    0.49
    Activations Density 0.088%

    No Known Activations