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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 15696
    Prev
    Next
    INDEX
    Explanations

    phrases related to research feasibility and practical implications

    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
     investimentos
    -0.42
    convite
    -0.42
     Estudios
    -0.42
     inwesty
    -0.42
    Skocz
    -0.40
     investasi
    -0.40
     Garantía
    -0.40
     tutkim
    -0.39
     colgantes
    -0.39
     inversiones
    -0.39
    POSITIVE LOGITS
    
    0.58
    #
    0.55
    
    0.52
    Hozzáférés
    0.51
    GraphicsUnit
    0.50
    IANGLES
    0.47
     OMITTED
    0.46
     الرحمن
    0.46
    WaitGroup
    0.45
    XDECREF
    0.45
    Activations Density 0.448%

    No Known Activations