© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1381
    Prev
    Next
    INDEX
    Explanations

    terms related to filtering in data processing or programming contexts

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

    "filter" and its variations

    np_acts-logits-general · gemini-2.0-flash

    filter operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nextProps
    -0.89
    +#+#
    -0.86
    BeginContext
    -0.84
     препратки
    -0.83
    ymce
    -0.82
    TagMode
    -0.80
    ruvate
    -0.78
    
    -0.77
     للاسماء
    -0.75
     pyruvate
    -0.74
    POSITIVE LOGITS
     filters
    1.74
     filter
    1.66
    filters
    1.60
     Filters
    1.58
     Filter
    1.55
    Filter
    1.50
    filter
    1.49
    Filters
    1.46
     filtering
    1.43
     FILTER
    1.42
    Activations Density 0.130%

    No Known Activations