© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12364
    Prev
    Next
    INDEX
    Explanations

    assertive statements and recommendations

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

    "Definitely" and related adverbs

    np_acts-logits-general · gemini-2.0-flash

    expressing certainty

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     aveug
    -0.54
    ScopeManager
    -0.49
     abstrait
    -0.48
     informatique
    -0.48
     armées
    -0.47
     écou
    -0.47
     Meksika
    -0.47
     Jerusalén
    -0.47
     Grèce
    -0.45
    berdayakan
    -0.45
    POSITIVE LOGITS
     definitely
    1.13
     certainly
    1.01
     Definitely
    1.00
    definitely
    0.96
    Definitely
    0.94
    certainly
    0.94
     Certainly
    0.90
     definately
    0.90
    Certainly
    0.84
     certamente
    0.77
    Activations Density 0.166%

    No Known Activations