Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12833
    Prev
    Next
    INDEX
    Explanations

    conditional statements and checks for equality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     strpos
    -0.48
     CURLOPT
    -0.47
     WebDriverWait
    -0.47
     touché
    -0.45
     navigation
    -0.45
     appointments
    -0.45
     QLabel
    -0.44
     pitch
    -0.44
     onCreateView
    -0.43
     DS
    -0.43
    POSITIVE LOGITS
    EDEFAULT
    0.48
     незавершена
    0.43
     muñecas
    0.43
    parsedMessage
    0.42
    følge
    0.41
     paille
    0.40
     miniaturka
    0.40
    édia
    0.39
     almohada
    0.39
     bParam
    0.39
    Activations Density 0.180%

    No Known Activations