© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 13197
    Prev
    Next
    INDEX
    Explanations

    references to different types of soil and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to soil properties, types, and characteristics in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.60
    awtextra
    -0.54
    .*")]
    -0.52
    ztat
    -0.48
    ▬▬▬▬
    -0.45
    oas
    -0.44
    vex
    -0.43
    --}}
    -0.43
    WebVitals
    -0.43
     kasarigan
    -0.43
    POSITIVE LOGITS
     soil
    1.72
     Soil
    1.44
    soil
    1.43
    Soil
    1.35
     soils
    1.31
     SOIL
    1.28
     dirt
    1.26
     sand
    1.20
     Soils
    1.09
    Soils
    1.02
    Activations Density 0.208%

    No Known Activations