© 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. 7-GEMMASCOPE-RES-16K
    11. 15637
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to solid substances or states, particularly in scientific and medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wireType
    -0.56
     SwitchCompat
    -0.52
     CreateTagHelper
    -0.48
     fréquence
    -0.47
     frequency
    -0.47
     Lorentz
    -0.46
    Ƚ
    -0.46
    gettimeofday
    -0.45
     desmotivaciones
    -0.45
     methylation
    -0.45
    POSITIVE LOGITS
     solid
    3.19
    solid
    3.17
    Solid
    3.06
     Solid
    3.03
     SOLID
    2.72
    SOLID
    2.59
     sólido
    2.19
     solide
    2.11
     sólidos
    2.09
     solids
    2.02
    Activations Density 0.089%

    No Known Activations