© 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. 15090
    Prev
    Next
    INDEX
    Explanations

    various contexts in which respect is discussed or emphasized

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

    "Respect" or "detect" followed by other words

    np_acts-logits-general · gemini-2.0-flash

    respect and detecting

    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
     kasarigan
    -0.71
     Anſ
    -0.66
     getItemId
    -0.65
    saraba
    -0.63
    inghouse
    -0.62
     Aura
    -0.60
     numberOfRows
    -0.60
    ownership
    -0.60
    Aura
    -0.60
     millennials
    -0.60
    POSITIVE LOGITS
    detect
    0.60
     detect
    0.57
    detectChanges
    0.54
     Detect
    0.49
     detects
    0.47
     detection
    0.46
    Inject
    0.44
     detec
    0.43
    tc
    0.42
     DETECT
    0.41
    Activations Density 0.245%

    No Known Activations