© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 8518
    Prev
    Next
    INDEX
    Explanations

    names of individuals and references to specific legal cases or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ******/
    -0.39
    *)((
    -0.36
    InteropServices
    -0.35
     GetEnumerator
    -0.35
    Pfalz
    -0.34
    []>(
    -0.33
    ")==
    -0.32
     =='
    -0.32
     plaît
    -0.32
     berapa
    -0.32
    POSITIVE LOGITS
     J
    1.43
     M
    1.18
     C
    1.16
     E
    1.15
     A
    1.14
     R
    1.13
     D
    1.09
     L
    1.07
     P
    1.06
     W
    1.05
    Activations Density 0.964%

    No Known Activations