Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2007
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features of synthesizers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     privée
    -0.51
     maschile
    -0.50
     riuscito
    -0.48
    nodeValue
    -0.47
    Viewing
    -0.47
     accepté
    -0.47
    HandleFunc
    -0.47
     Teller
    -0.46
     intérieur
    -0.46
     privato
    -0.46
    POSITIVE LOGITS
     MIDI
    0.77
     instrument
    0.76
     reverb
    0.75
     synth
    0.72
     guitar
    0.72
     instruments
    0.71
     Instrument
    0.70
     musicians
    0.66
     onstage
    0.66
     preamp
    0.65
    Activations Density 0.167%

    No Known Activations