© 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. 20-GEMMASCOPE-RES-16K
    11. 4464
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to disability claims and adjudications

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

    Preceding "Secretary" or "Administrative"

    np_acts-logits-general · gemini-2.0-flash

    legal appeals

    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
    jsxFileName
    -0.55
    BeginContext
    -0.53
    
    -0.52
    OpenHelper
    -0.47
    CURLOPT
    -0.45
     chúc
    -0.43
     plonge
    -0.43
     Krä
    -0.43
     законо
    -0.42
     surla
    -0.42
    POSITIVE LOGITS
     appeal
    1.26
     appeals
    1.20
    Appe
    1.12
     Appeal
    1.11
     Appeals
    1.10
    Appeal
    1.08
    appeal
    1.03
     appealed
    1.02
     APPEAL
    0.96
    appe
    0.94
    Activations Density 1.600%

    No Known Activations