© 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. 30-GEMMASCOPE-RES-16K
    11. 7447
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases about scenic locations and outdoor experiences

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Locations near water (rivers, seas, etc.)

    np_acts-logits-general · gemini-2.0-flash

    river bank locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    entro
    -0.30
    lijf
    -0.29
     Centro
    -0.28
     concentra
    -0.27
     Republican
    -0.27
     Dentro
    -0.27
     concentr
    -0.27
     Regional
    -0.27
    kammer
    -0.27
    újo
    -0.27
    POSITIVE LOGITS
     waterfront
    1.45
     seashore
    1.41
     seaside
    1.38
     beachfront
    1.34
     coastal
    1.30
     riverside
    1.28
    coastal
    1.19
     ocean
    1.16
     beach
    1.16
     Waterfront
    1.15
    Activations Density 0.257%

    No Known Activations