© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 5885
    Prev
    Next
    INDEX
    Explanations

    references to authors, particularly poets and judges, and their achievements or affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     polaire
    -0.42
     INTERESAR
    -0.41
     vectorielle
    -0.38
    InjectMocks
    -0.38
     disposiciones
    -0.37
     muut
    -0.37
     familières
    -0.36
     inoxydable
    -0.35
    verifyException
    -0.35
     niño
    -0.35
    POSITIVE LOGITS
    sizeCache
    0.52
     defaultstate
    0.45
    enderror
    0.44
     ProtoMessage
    0.42
    -------------</
    0.42
    RTEX
    0.42
    
    0.42
     שוליים
    0.42
    DockStyle
    0.41
     NDEBUG
    0.41
    Activations Density 1.518%

    No Known Activations