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. 15810
    Prev
    Next
    INDEX
    Explanations

    words related to genes and gene products, particularly verbs like "encoding" and nouns like "proteins" or "enzymes".

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @myinzi123

    genes and their corresponding protein functions

    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
     AssemblyCulture
    -0.70
    NameInMap
    -0.64
    principalColumn
    -0.56
    :✨
    -0.55
    HandleFunc
    -0.53
     Autorizaciones
    -0.52
     Autorisations
    -0.51
     Վերցված
    -0.50
    yakarta
    -0.49
    CodedInputStream
    -0.48
    POSITIVE LOGITS
    edan
    0.43
    Cubit
    0.36
     dinosaurs
    0.35
    JScrollPane
    0.32
     joaat
    0.32
     Konf
    0.32
    "]();
    0.32
    ScopeManager
    0.31
     worms
    0.30
    isContained
    0.30
    Activations Density 1.340%

    No Known Activations