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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8380
    Prev
    Next
    INDEX
    Explanations

    mentions of orchestras and their conductors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mpada
    -0.42
     roller
    -0.41
     Gitar
    -0.40
     alimentaria
    -0.40
    phazard
    -0.40
     antaranya
    -0.39
     dependiendo
    -0.39
    enteuer
    -0.38
    Bakgrunnsstoff
    -0.38
     ayuntamiento
    -0.37
    POSITIVE LOGITS
    TestingModule
    0.60
    Classical
    0.55
    concert
    0.52
     virtuoso
    0.52
     ſch
    0.51
    Aholisi
    0.51
     Classical
    0.50
    Concert
    0.48
     ſte
    0.48
    classical
    0.48
    Activations Density 0.119%

    No Known Activations