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

    Neuronpedia

    Jacobian LensNEW
    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. 15-GEMMASCOPE-RES-16K
    11. 6998
    Prev
    Next
    INDEX
    Explanations

    terms related to changes in quantity or frequency, particularly in the context of increasing amounts or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erv
    -0.44
    perma
    -0.44
     ogóle
    -0.43
    badah
    -0.43
     El
    -0.43
    ございました
    -0.43
     awakeFromNib
    -0.42
    iten
    -0.41
    chie
    -0.41
     Oba
    -0.40
    POSITIVE LOGITS
     increasingly
    1.64
     progressively
    1.40
    越来越
    1.32
    越來越
    1.26
    increasing
    1.13
     Increasing
    1.13
     increasing
    1.12
    Increasing
    1.09
     gradually
    1.09
     coraz
    1.06
    Activations Density 0.346%

    No Known Activations