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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6041
    Prev
    Next
    INDEX
    Explanations

    elements related to leadership and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.50
     <>",
    -0.46
     tradição
    -0.43
     TAMBIÉN
    -0.42
    awaiter
    -0.40
     tajam
    -0.38
     gustaba
    -0.38
     escena
    -0.38
    BeginContext
    -0.38
     alternativas
    -0.38
    POSITIVE LOGITS
     Chwiliwch
    0.43
     daily
    0.42
    ніципалі
    0.41
     interact
    0.41
    inha
    0.40
    archical
    0.40
    beha
    0.39
     tamp
    0.38
     ReSharper
    0.38
     duties
    0.38
    Activations Density 0.675%

    No Known Activations