© 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. 2-GEMMASCOPE-RES-16K
    11. 560
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific assays and methodologies, particularly related to tropism and viral characterization

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     incest
    -0.41
     alé
    -0.40
    ӹ
    -0.39
     UIAlert
    -0.38
     kaarangay
    -0.38
    principalTable
    -0.37
    меч
    -0.37
    Geplaatst
    -0.36
    </tfoot>
    -0.36
    BDD
    -0.36
    POSITIVE LOGITS
    Tro
    0.67
    ography
    0.67
     Bron
    0.66
     bron
    0.65
    Bron
    0.64
     Tro
    0.63
     invoice
    0.62
    ograph
    0.60
    ographic
    0.60
     trophy
    0.59
    Activations Density 0.485%

    No Known Activations