© 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. 3-GEMMASCOPE-RES-16K
    11. 6068
    Prev
    Next
    INDEX
    Explanations

    references to functions and signals in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TestingModule
    -0.42
     FetchType
    -0.39
    ContentAlignment
    -0.39
     ketat
    -0.38
    }{*}{
    -0.37
     Instrumente
    -0.37
     zufolge
    -0.35
     Krakowie
    -0.35
     mechanics
    -0.35
     EnglishChoose
    -0.34
    POSITIVE LOGITS
     signal
    1.14
     Signal
    1.13
    Signal
    1.02
    signal
    1.02
     SIGNAL
    0.92
     Signals
    0.90
     signals
    0.89
    SIGNAL
    0.88
    Signals
    0.84
     regime
    0.80
    Activations Density 0.075%

    No Known Activations