© 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. 10283
    Prev
    Next
    INDEX
    Explanations

    words related to specific scientific measurements or units

    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
     препратки
    -0.59
    IUrlHelper
    -0.58
     EconPapers
    -0.52
    rungsseite
    -0.41
     CURIAM
    -0.40
    webElementXpaths
    -0.39
     AspNetCore
    -0.39
    neté
    -0.38
     дописавши
    -0.37
    optionalTypeArgs
    -0.37
    POSITIVE LOGITS
    rm
    1.73
     rm
    1.50
    RM
    1.47
     RM
    1.38
    orm
    1.34
    Rm
    1.19
    rms
    1.18
    رم
    1.16
    irm
    1.10
    arm
    1.09
    Activations Density 0.641%

    No Known Activations