© 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. 27-GEMMASCOPE-RES-16K
    11. 12860
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to movement and direction

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     tand
    -0.34
    BagLayout
    -0.32
     Cost
    -0.28
     hjär
    -0.28
     olan
    -0.27
     RestTemplate
    -0.27
    medium
    -0.27
    entierung
    -0.27
    ByUser
    -0.26
     Référence
    -0.26
    POSITIVE LOGITS
     down
    0.78
    endphp
    0.73
     back
    0.72
     into
    0.70
     away
    0.68
    }],
    0.67
     ddelweddau
    0.66
     out
    0.66
    OGND
    0.66
     off
    0.63
    Activations Density 0.384%

    No Known Activations