© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4738
    Prev
    Next
    INDEX
    Explanations

    expressions of agreement and consensus

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

    phrases expressing agreement or consent, particularly with words like "agree" and "to".

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     Marin
    -0.50
     Benth
    -0.46
     Il
    -0.46
     Lud
    -0.46
    Marin
    -0.45
     Thors
    -0.45
     lud
    -0.44
    Il
    -0.44
    нент
    -0.44
     Marion
    -0.44
    POSITIVE LOGITS
     agreement
    1.13
     agree
    1.13
     Agree
    1.12
    agree
    1.07
     Agreement
    1.06
    agreement
    1.05
    Agree
    1.02
    Agreement
    1.00
     agrees
    0.99
     agreeing
    0.99
    Activations Density 0.105%

    No Known Activations