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

    Neuronpedia

    Jacobian LensNEW
    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. 5471
    Prev
    Next
    INDEX
    Explanations

    references to different types of services

    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
     knots
    -0.41
     Estadual
    -0.35
    mmas
    -0.35
    wahl
    -0.34
     Lager
    -0.33
     the
    -0.32
     Aussch
    -0.32
    counter
    -0.31
    口袋
    -0.31
     counter
    -0.31
    POSITIVE LOGITS
     services
    3.50
    services
    3.09
     Services
    3.00
     SERVICES
    2.92
    Services
    2.89
    SERVICES
    2.63
     servicios
    2.59
     diensten
    2.48
     serviços
    2.45
    ervices
    2.38
    Activations Density 0.119%

    No Known Activations