© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7418
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "below" and related instructions to reference accompanying information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     AssemblyTitle
    -0.84
     AssemblyVersion
    -0.63
     NavController
    -0.55
    دانشنامهٔ
    -0.54
     ''}
    -0.53
    ()");
    -0.50
     itemName
    -0.49
     oldValue
    -0.49
    inSlope
    -0.47
    useNewUrlParser
    -0.47
    POSITIVE LOGITS
     below
    0.94
     Below
    0.85
    Below
    0.84
    below
    0.77
     abaixo
    0.69
     hieronder
    0.67
     bellow
    0.67
     ниже
    0.62
     BELOW
    0.60
     continuación
    0.59
    Activations Density 0.110%

    No Known Activations