© 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. 8233
    Prev
    Next
    INDEX
    Explanations

    specific variables and conditions related to computer programs and their execution

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

    Follows "is" and precedes a negative word/concept

    np_acts-logits-general · gemini-2.0-flash

    states or conditions

    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
    ีย์
    -0.57
     inilah
    -0.54
    MessageOf
    -0.54
     zwar
    -0.53
     препратки
    -0.51
    expandindo
    -0.50
     disponibilités
    -0.50
    getPackageName
    -0.50
    Глав
    -0.50
     BorderSide
    -0.49
    POSITIVE LOGITS
     or
    0.79
     algún
    0.64
     Walkover
    0.63
    paramref
    0.62
     algum
    0.60
     any
    0.60
     alguna
    0.58
     perchance
    0.58
     eller
    0.58
     nějak
    0.57
    Activations Density 0.603%

    No Known Activations