© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5357
    Prev
    Next
    INDEX
    Explanations

    terms related to types, categories, and classification

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

    following "all", "any", "other", or "first"

    np_acts-logits-general · gemini-2.0-flash

    any specific category

    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
    -1.01
     measles
    -0.72
     ISNI
    -0.62
    ChromeDriver
    -0.62
     ChromeDriver
    -0.61
     diapers
    -0.60
     rabies
    -0.59
     biceps
    -0.59
     pediatrician
    -0.59
     glaucoma
    -0.59
    POSITIVE LOGITS
    こういった
    0.79
    ^(@)
    0.72
    CELLANEOUS
    0.67
     الرياضيه
    0.64
     sowas
    0.64
    actéristique
    0.62
    %;">
    0.61
     }}$}
    0.59
    こういう
    0.59
     ſmall
    0.59
    Activations Density 0.679%

    No Known Activations