© 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 EvalsExportsinterp-engineNEWAPI 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. 1662
    Prev
    Next
    INDEX
    Explanations

    terms related to data structures and their content

    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
     ſche
    -0.57
     المعيارى
    -0.57
     aliexpress
    -0.54
    (!__
    -0.53
     fubject
    -0.52
     ſy
    -0.51
     ſind
    -0.50
     houſe
    -0.50
     ſich
    -0.49
     ſta
    -0.49
    POSITIVE LOGITS
     contains
    1.47
    Contains
    1.21
    contains
    1.21
     Contains
    1.19
     boasts
    1.08
     includes
    1.07
     contiene
    1.02
     possesses
    1.01
     obsahuje
    1.00
     содержит
    0.99
    Activations Density 0.144%

    No Known Activations