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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6244
    Prev
    Next
    INDEX
    Explanations

    references to economic and political systems and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    참고
    -0.49
     wikipagina
    -0.49
     étro
    -0.43
     activiteiten
    -0.42
     aktif
    -0.42
    diensten
    -0.39
    keur
    -0.39
     titulada
    -0.39
     actief
    -0.39
     irmã
    -0.38
    POSITIVE LOGITS
    IUrlHelper
    0.79
     AttributeSet
    0.69
     billions
    0.59
     AssemblyVersion
    0.53
     patriotism
    0.51
     statesmen
    0.50
     billionaires
    0.50
     capitalism
    0.50
     phosphates
    0.49
     capitalists
    0.49
    Activations Density 1.014%

    No Known Activations