© 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. 3-GEMMASCOPE-RES-16K
    11. 2740
    Prev
    Next
    INDEX
    Explanations

    references to criminal charges and legal allegations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    trusted
    -0.45
     trusted
    -0.43
    ngths
    -0.42
    tagHelperRunner
    -0.40
    ]-->
    -0.40
    SpringBootTest
    -0.39
     closed
    -0.39
    }],
    -0.39
     Gerard
    -0.39
     Catawiki
    -0.39
    POSITIVE LOGITS
     charges
    0.91
     ingredients
    0.75
     Charges
    0.74
    Ingredients
    0.73
     ingredient
    0.67
    ingredients
    0.66
     Ingredients
    0.65
    Ingredient
    0.64
     coefficients
    0.63
     Ingredient
    0.63
    Activations Density 0.109%

    No Known Activations