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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7895
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of "soil" and its various characteristics and factors associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tanleria
    -0.43
    ForValue
    -0.40
     actionPerformed
    -0.37
    ________________
    -0.36
    __((
    -0.36
    specialchars
    -0.35
    BufferException
    -0.35
    IBarButtonItem
    -0.35
     passage
    -0.34
    ständ
    -0.34
    POSITIVE LOGITS
    Soil
    0.70
     soil
    0.69
     Soil
    0.66
     SOIL
    0.65
     soils
    0.59
     Soils
    0.58
     specimens
    0.57
    Soils
    0.56
    rungsseite
    0.54
     species
    0.54
    Activations Density 0.286%

    No Known Activations