© 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. 15-GEMMASCOPE-RES-16K
    11. 11637
    Prev
    Next
    INDEX
    Explanations

    verbs indicating transformation or change

    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
     nadzieję
    -0.76
     termica
    -0.65
     pattes
    -0.65
     marbles
    -0.63
     căr
    -0.63
     urme
    -0.63
     nadzie
    -0.60
     faptul
    -0.59
     WARN
    -0.59
     Langue
    -0.58
    POSITIVE LOGITS
     become
    1.30
     became
    1.27
     becoming
    1.23
     becomes
    1.22
     Becomes
    1.13
    becomes
    1.13
    became
    1.10
    become
    1.08
    becoming
    1.07
     Becoming
    1.05
    Activations Density 0.081%

    No Known Activations