© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 9637
    Prev
    Next
    INDEX
    Explanations

    proper nouns and significant identified groups or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnimationsModule
    -0.60
     AssemblyCulture
    -0.59
     kasarigan
    -0.59
    GenerationType
    -0.58
     disambiguazione
    -0.57
    principalTable
    -0.55
    ChildScrollView
    -0.54
     صوتيه
    -0.51
    PropertyChanging
    -0.51
    VPB
    -0.50
    POSITIVE LOGITS
     ensayo
    0.47
     registered
    0.47
     registró
    0.44
     REGISTER
    0.44
    注册
    0.43
     Christi
    0.42
     regist
    0.41
     register
    0.41
     registro
    0.41
    hoe
    0.40
    Activations Density 1.866%

    No Known Activations