© 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. 1-GEMMASCOPE-RES-16K
    11. 8537
    Prev
    Next
    INDEX
    Explanations

    the presence of the term "Ran"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RoutingModule
    -0.39
    InjectMocks
    -0.38
     فريبيس
    -0.34
     éclat
    -0.34
     encuent
    -0.34
    addPreferredGap
    -0.33
    Rohy
    -0.33
     ejer
    -0.32
    ChildScrollView
    -0.32
    ภา
    -0.31
    POSITIVE LOGITS
     Ran
    2.27
    Ran
    2.27
    ran
    2.25
    RAN
    1.98
     RAN
    1.86
     ran
    1.80
    ranch
    1.61
     Ranch
    1.52
    ран
    1.42
     rancher
    1.41
    Activations Density 0.203%

    No Known Activations