© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30507
    Prev
    Next
    INDEX
    Explanations

    the presence of the letter 'i' and 'e' in various contexts

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

    i.e. or e.g. abbreviations

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    AsUp
    -0.97
     ſeveral
    -0.75
     preſent
    -0.73
    Referanser
    -0.70
     Reſ
    -0.69
     pleaſure
    -0.69
    GEBURTSDATUM
    -0.68
    Autoritní
    -0.67
    OGND
    -0.66
     diſt
    -0.66
    POSITIVE LOGITS
     např
    0.74
     namely
    0.65
    viz
    0.59
    zyna
    0.58
     viz
    0.58
     GenerationType
    0.58
     piele
    0.57
     cardinality
    0.56
     tức
    0.56
     notably
    0.55
    Activations Density 0.045%

    No Known Activations