© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 89942
    Prev
    Next
    INDEX
    Explanations

    references to significant individuals or categories associated with "Sal"

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

    words starting with Sal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlType
    -0.41
    pgterms
    -0.36
     femininas
    -0.34
    TagMode
    -0.34
     econômica
    -0.33
    XmlAccessorType
    -0.33
     todella
    -0.32
    keyColumn
    -0.32
     stør
    -0.32
    EndContext
    -0.32
    POSITIVE LOGITS
     Sal
    0.87
    Sal
    0.84
     SAL
    0.82
     sal
    0.78
    SAL
    0.73
    sal
    0.71
    Sali
    0.66
     Salim
    0.66
     Salinity
    0.65
     Sali
    0.64
    Activations Density 0.041%

    No Known Activations