© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9564
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons and classifications

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

    followed by categories of adjectives

    np_acts-logits-general · gemini-2.0-flash

    mental or commercial

    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
    
    -0.74
     comets
    -0.65
     sherds
    -0.65
     prunes
    -0.62
    Millan
    -0.60
     pamamagitan
    -0.58
     kanyang
    -0.57
     Lillie
    -0.56
     divisors
    -0.56
     amines
    -0.56
    POSITIVE LOGITS
     illetve
    0.62
     кӀ
    0.60
    Datuak
    0.59
    +#+#
    0.55
     non
    0.53
    localctx
    0.51
     valamint
    0.51
    cellaneous
    0.49
    ()];
    0.48
     EClass
    0.48
    Activations Density 0.486%

    No Known Activations