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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 7783
    Prev
    Next
    INDEX
    Explanations

    numerical data related to demographic and health metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     capacidades
    -0.37
    łaści
    -0.33
     añadido
    -0.33
     ampliación
    -0.33
     exigencias
    -0.32
     künf
    -0.31
    دانشنامهٔ
    -0.31
     limitada
    -0.31
    Xna
    -0.31
     autoridades
    -0.31
    POSITIVE LOGITS
     categorical
    0.74
     Median
    0.71
     median
    0.70
     days
    0.69
     Proportion
    0.69
     Avg
    0.68
     Days
    0.68
     perc
    0.68
     Months
    0.68
     outliers
    0.68
    Activations Density 2.237%

    No Known Activations