© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12983
    Prev
    Next
    INDEX
    Explanations

    names or titles of people and their roles or actions

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

    Word precedes a preposition/determiner

    np_acts-logits-general · gemini-2.0-flash

    a certain someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lisäksi
    -0.62
     both
    -0.61
     zarówno
    -0.61
     wszyst
    -0.59
     semuanya
    -0.57
     tuturor
    -0.56
     nejen
    -0.56
     either
    -0.55
     zowel
    -0.54
     meeste
    -0.53
    POSITIVE LOGITS
    某
    0.69
     إحدى
    0.64
    とある
    0.60
     egyik
    0.59
     someone
    0.59
     eines
    0.58
    たまたま
    0.58
     salah
    0.57
    someone
    0.55
    ある
    0.54
    Activations Density 1.120%

    No Known Activations