© 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. 38-GEMMASCOPE-RES-16K
    11. 12058
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables related to physical equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     influencia
    -0.42
     preuves
    -0.42
     Verhalten
    -0.41
     herencia
    -0.40
     goûts
    -0.40
     actitudes
    -0.40
     Erscheinung
    -0.39
     asamblea
    -0.39
     negociación
    -0.39
     fashion
    -0.39
    POSITIVE LOGITS
    msub
    0.56
    SceneManagement
    0.53
    memoized
    0.53
    Vidite
    0.49
    RT
    0.48
    PerformLayout
    0.47
    cobra
    0.45
    Tamb
    0.44
     Pref
    0.44
     disponibilités
    0.44
    Activations Density 2.148%

    No Known Activations