© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 2256
    Prev
    Next
    INDEX
    Explanations

    phrases related to merging and processing datasets

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

    Combining results or sentences

    np_acts-logits-general · gemini-2.0-flash

    accumulating results together

    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
    parsedMessage
    -0.56
    धारण
    -0.55
    wnież
    -0.50
     DLP
    -0.50
    CPtr
    -0.49
    ännande
    -0.49
    polarized
    -0.49
    owohl
    -0.47
     Both
    -0.46
    ANTLR
    -0.46
    POSITIVE LOGITS
     cumulative
    1.11
     cumul
    1.09
     collectively
    1.04
     together
    0.98
     stacking
    0.96
     collective
    0.91
     stacked
    0.89
     accum
    0.86
     aggregate
    0.85
     combined
    0.85
    Activations Density 1.051%

    No Known Activations