© 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. 21-GEMMASCOPE-RES-16K
    11. 11941
    Prev
    Next
    INDEX
    Explanations

    technical specifications and programming commands related to functions and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.79
    OGND
    -0.73
    sizeCache
    -0.71
     propOrder
    -0.70
    AndEndTag
    -0.64
    AddTagHelper
    -0.61
     Autorizaciones
    -0.60
    ValueStyle
    -0.60
    RegistryLite
    -0.59
    よいよ
    -0.59
    POSITIVE LOGITS
     tilbake
    0.52
     revert
    0.51
     reverting
    0.51
     normal
    0.48
     kembali
    0.45
     обратно
    0.45
     reverted
    0.44
     reset
    0.43
     restoring
    0.42
     back
    0.42
    Activations Density 0.465%

    No Known Activations