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. 33-GEMMASCOPE-RES-16K
    6. 11579
    Prev
    Next
    INDEX
    Explanations

    references to political structures and legislative bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectMocks
    -0.57
    Diweddarwch
    -0.50
    日閲覧
    -0.49
    पया
    -0.48
     autorytatywna
    -0.48
    跆
    -0.47
     onBind
    -0.47
    XmlAccessorType
    -0.46
    ternut
    -0.45
    appoint
    -0.45
    POSITIVE LOGITS
     assembly
    1.27
     Assembly
    1.25
     Council
    1.17
     council
    1.11
    Assembly
    1.07
     assemblies
    1.05
    assembly
    1.03
     ASSEMBLY
    1.00
    Council
    1.00
     councils
    0.94
    Activations Density 0.313%

    No Known Activations