© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 17602
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate potential or significant benefits in various contexts

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

    potential for positive outcomes

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Affirmed
    -0.43
    blogger
    -0.39
     queſta
    -0.38
    }\]
    -0.38
     mã
    -0.37
    Affiliate
    -0.36
     âm
    -0.36
    ifolium
    -0.36
     Gefühl
    -0.35
    quium
    -0.35
    POSITIVE LOGITS
     potential
    0.81
    潜力
    0.68
     future
    0.66
     Potential
    0.66
     potentiel
    0.65
    Potential
    0.65
     potentials
    0.65
     potencial
    0.64
    potential
    0.61
     potenciales
    0.60
    Activations Density 0.053%

    No Known Activations