© 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. 41-GEMMASCOPE-RES-16K
    11. 13617
    Prev
    Next
    INDEX
    Explanations

    patterns or specific sequences in alphanumeric or coded strings

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    c
    -1.37
    f
    -1.16
    d
    -0.93
    cN
    -0.63
    cB
    -0.59
    cX
    -0.57
    cides
    -0.52
    cF
    -0.51
    cT
    -0.51
    cE
    -0.51
    POSITIVE LOGITS
     JpaRepository
    0.44
     disambiguazione
    0.42
     ujednoznacz
    0.39
     CreateTagHelper
    0.39
    openConnection
    0.38
     actionMode
    0.36
    HideFlags
    0.36
    jsonwebtoken
    0.35
    Insee
    0.35
    ffold
    0.35
    Activations Density 0.492%

    No Known Activations