© 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. 2-GEMMASCOPE-RES-16K
    11. 8400
    Prev
    Next
    INDEX
    Explanations

    numerical values or references to quantities and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    躇
    -0.77
    ScopeManager
    -0.70
    MessageTagHelper
    -0.68
    RegistryLite
    -0.66
     AssemblyCulture
    -0.65
     transfieras
    -0.65
    ContentLoaded
    -0.64
    tagHelperRunner
    -0.63
    StructEnd
    -0.63
    CrossRef
    -0.63
    POSITIVE LOGITS
     Bewußt
    0.42
    
    0.38
    [++
    0.33
     vergangenen
    0.32
    )("
    0.28
     letz
    0.27
    ³/
    0.27
    Vegeu
    0.26
     näch
    0.25
     przesz
    0.25
    Activations Density 0.806%

    No Known Activations