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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5106
    Prev
    Next
    INDEX
    Explanations

    technical terms and expressions related to RNA and DNA sequencing methodologies

    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
     Tilt
    -0.37
     Power
    -0.37
     Fat
    -0.36
     Add
    -0.35
     Sport
    -0.35
     Mag
    -0.35
     J
    -0.34
     Side
    -0.34
     H
    -0.34
     inj
    -0.34
    POSITIVE LOGITS
     estadounid
    0.76
     indígen
    0.76
     increí
    0.74
     disambiguazione
    0.73
     plufieurs
    0.68
     desmotivaciones
    0.66
     geſ
    0.65
    rungsseite
    0.65
     Bioinformatics
    0.64
     Italijani
    0.61
    Activations Density 2.801%

    No Known Activations