© 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. 23-GEMMASCOPE-RES-16K
    11. 4390
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "too" in varying contexts and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rhestr
    -0.75
    ly
    -0.59
    了
    -0.58
    mente
    -0.57
     inoxydable
    -0.56
    maßen
    -0.55
    jarse
    -0.55
    ाहरण
    -0.54
    に
    -0.53
     Mammals
    -0.53
    POSITIVE LOGITS
    thy
    0.83
    ths
    0.66
     much
    0.65
     often
    0.61
     InputDecoration
    0.60
     late
    0.57
    protoimpl
    0.56
     FetchType
    0.56
    often
    0.55
    లాలు
    0.55
    Activations Density 0.044%

    No Known Activations