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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8747
    Prev
    Next
    INDEX
    Explanations

    keywords related to filters and filtering processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     huelga
    -0.43
     caza
    -0.40
     aeropuerto
    -0.38
     secretario
    -0.37
     buying
    -0.36
     Gegner
    -0.36
    XMLHttpRequest
    -0.36
     financiación
    -0.35
     dragón
    -0.35
    Executable
    -0.35
    POSITIVE LOGITS
     filters
    1.31
     Filters
    1.23
    filters
    1.09
     filtering
    1.04
     Filtering
    1.03
    Filters
    1.00
     filtration
    0.96
     filter
    0.95
     Filtration
    0.94
     Filter
    0.90
    Activations Density 0.265%

    No Known Activations